{ "_about": "CommoVision gold data dictionary, generated from the enforced schema contracts; do not edit by hand. Regenerate: just gold-data-dictionary.", "tables": { "gold_directional_surveys": { "description": "Full wellbore trajectories: one row per survey station (a measured-depth reading along a wellbore leg), with inclination, azimuth, true vertical depth, and position in WGS84. Every filed reading is kept: planned (proposed) surveys as well as as-drilled, and superseded filings alongside the latest, so you can compare plan against actual. For the current as-drilled trajectory, filter is_proposed = false and is_latest_version = true. This is the table for accurate lateral placement, well spacing, and landing-zone work.", "tier": "portal", "primary_key": [ "station_id" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "station_id", "type": "string", "nullable": false, "description": "Globally unique station identifier (opaque string), this table's primary key. Distinct filings and plan-vs-as-drilled readings of the same well/leg/depth coexist as separate rows; for the canonical trajectory filter is_proposed = false AND is_latest_version = true. Never parse substrings out of it.\n", "enum": [] }, { "name": "well_id", "type": "string", "nullable": false, "description": "Join key to the well register (gold_wells).\n", "enum": [] }, { "name": "completion_id", "type": "string", "nullable": true, "description": "Join key to gold_well_completions. Links the survey leg to its completion event: the vertical hole and first lateral to the initial completion; later laterals and sidetracks to recompletions by date order.\n", "enum": [] }, { "name": "station_sequence", "type": "int32", "nullable": false, "description": "Row number of the station within its (well, leg, filing), ordered by measured depth; starts at 1. A filing that carries both a proposed and an as-drilled survey numbers each set separately.\n", "enum": [] }, { "name": "leg", "type": "string", "nullable": false, "description": "Wellbore leg code (VERT, DIR, LAT1, STK2, ...). Within a single multi-survey filing, LAT1/LAT2 distinguish the laterals; across separate filings the same lateral defaults back to LAT1 unless the operator labeled it.\n", "enum": [] }, { "name": "leg_type", "type": "string", "nullable": true, "description": "The leg's classified type: vertical, directional, lateral, or sidetrack.\n", "enum": [ "vertical", "directional", "lateral", "sidetrack" ] }, { "name": "leg_sequence", "type": "int32", "nullable": true, "description": "Numeric sequence of the leg within its type (LAT1 = 1, LAT2 = 2; vertical/directional legs = 1).\n", "enum": [] }, { "name": "md", "type": "float64", "nullable": false, "description": "Measured depth in feet. The station ordering key.\n", "enum": [] }, { "name": "inclination", "type": "float64", "nullable": true, "description": "Wellbore deviation from vertical in degrees (0 = vertical, 90 = horizontal).\n", "enum": [] }, { "name": "azimuth", "type": "float64", "nullable": true, "description": "Compass bearing in degrees (0 = north, 90 = east).\n", "enum": [] }, { "name": "tvd", "type": "float64", "nullable": true, "description": "True vertical depth in feet. Source-provided where tvd_source = 'reported'; computed by the minimum-curvature method from measured depth, inclination and azimuth where 'min_curvature'.\n", "enum": [] }, { "name": "tvd_source", "type": "string", "nullable": true, "description": "Where this station's true vertical depth came from: reported = the source filing carried it; min_curvature = we computed it by the minimum-curvature method from measured depth, inclination and azimuth where the source omitted it. NULL exactly when tvd is NULL. Filter tvd_source = 'reported' for source-reported depths only. This is the per-station flag; the well-level gold_wells.tvd_source separately records which source tier supplied the well's headline TVD.\n", "enum": [ "reported", "min_curvature" ] }, { "name": "position_source", "type": "string", "nullable": true, "description": "Where this station's published position (latitude/longitude) came from: reported = the source filing carried the position (printed offsets from the surface location, or absolute coordinates we convert to WGS84); identity_inferred = the filing printed the position values but did not label the columns: we identified the north/south, east/west and vertical-section columns from the survey's own reference azimuth and internal geometry; min_curvature = we computed the position by the minimum-curvature method from measured depth, inclination and azimuth. NULL exactly when latitude/longitude are NULL. Filter position_source = 'reported' for source-asserted positions only.\n", "enum": [ "reported", "identity_inferred", "min_curvature" ] }, { "name": "latitude", "type": "float64", "nullable": true, "description": "Station latitude (WGS84). See position_source for whether it derives from a source-carried position or from our minimum-curvature computation.\n", "enum": [] }, { "name": "longitude", "type": "float64", "nullable": true, "description": "Station longitude (WGS84). See position_source for whether it derives from a source-carried position or from our minimum-curvature computation.\n", "enum": [] }, { "name": "doc_id", "type": "string", "nullable": false, "description": "Identifier of the source document this station was parsed from (opaque string). Stable, the same filing always yields the same id. Use source + source_id for the agency-side handle.\n", "enum": [] }, { "name": "source_id", "type": "string", "nullable": true, "description": "The agency-side handle of the source filing (e.g. the regulator's bulk filing id or document image id). Unique within a given source.\n", "enum": [] }, { "name": "source", "type": "string", "nullable": true, "description": "Which acquisition path the survey came from: daily_bulk (the regulator's bulk data feed) or completion_packet (PDFs from well completion packets).\n", "enum": [] }, { "name": "survey_date", "type": "date", "nullable": true, "description": "Date of the survey: the reported survey interval's end where the source publishes one, else the filing's header date (for proposed filings, the plan's own date). Used to order versions for is_latest_version: the latest-dated survey is the current version.\n", "enum": [] }, { "name": "sensor_type", "type": "string", "nullable": true, "description": "Survey sensor type: mwd = measurement-while-drilling (real-time, lower accuracy at depth); gyro = gyroscopic (higher accuracy, typically run after drilling); other = catch-all. NULL where the source doesn't say.\n", "enum": [ "mwd", "gyro", "other" ] }, { "name": "is_proposed", "type": "bool", "nullable": false, "description": "True if the survey is a pre-drill plan (a proposed trajectory); false if it is a post-drill as-drilled measurement. Never NULL: where the source filing does not label plan vs as-drilled, we resolve the value from that source's own filing semantics (a source whose unlabeled filings are as-drilled surveys reads false) and, where it is decisive, the survey's measured geometry; an explicit source label always stands. Pre-drill plans are kept so you can see the plan-vs-as-drilled delta and the full version history of a wellbore. For canonical bottom-hole position use is_proposed = false AND is_latest_version = true.\n", "enum": [] }, { "name": "is_latest_version", "type": "bool", "nullable": false, "description": "True for the row with the newest survey_date within (well, leg, measured depth); ties are broken deterministically. Latest does NOT imply as-drilled: a pre-drill plan can be the newest filed version; combine with is_proposed = false for canonical as-drilled positions.\n", "enum": [] } ], "regional_columns": [], "region_extras": { "bc": [ { "name": "wa_number", "type": "string", "description": "" } ], "nd": [ { "name": "file_no", "type": "int32", "description": "" } ], "ut": [ { "name": "construct_number", "type": "int32", "description": "" }, { "name": "citing_type", "type": "string", "description": "" } ] }, "serving_derived": [], "data_currency": [], "regions_live": [ "ar", "bc", "co", "la", "mi", "mt", "nd", "nm", "oh", "ok", "pa", "tx", "ut", "wv", "wy" ], "regions_live_names": [ "Arkansas", "British Columbia", "Colorado", "Louisiana", "Michigan", "Montana", "North Dakota", "New Mexico", "Ohio", "Oklahoma", "Pennsylvania", "Texas", "Utah", "West Virginia", "Wyoming" ] }, "gold_formation_name_mappings": { "description": "How reported formation names resolve to registry units. The same rock is reported under many names and spellings; each row maps one normalized reported name, within one basin, to its formation_id: the basin scope keeps same-named units in different basins apart. Apply it to your own data to get the same formation resolution we use.", "tier": "public_aggregate", "singleton_schema": "formations", "primary_key": [ "normalized_raw_name", "basin" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "normalized_raw_name", "type": "string", "nullable": false, "description": "Reported formation string after normalization.", "enum": [] }, { "name": "basin", "type": "string", "nullable": false, "description": "Basin the mapping applies in: the same basin vocabulary as gold_wells.basin.", "enum": [] }, { "name": "formation_id", "type": "string", "nullable": false, "description": "The registry unit this name resolves to (join to gold_formations).", "enum": [] }, { "name": "zone", "type": "string", "nullable": true, "description": "Informal bench or landing-zone label anchored to the formation (for example an upper/lower bench), where the reported name carries one.\n", "enum": [] }, { "name": "confidence", "type": "float64", "nullable": false, "description": "Mapping confidence, 0 to 1.", "enum": [] }, { "name": "source", "type": "string", "nullable": false, "description": "Where the mapping came from.", "enum": [] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "formations" ], "regions_live_names": [] }, "gold_formations": { "description": "Canonical registry of geological formations: the named rock units wells target and produce from. One row per stratigraphic unit (group, formation, member, or bed, plus broad age buckets where a source reports only a geological age), with its place in the hierarchy and stable links into public stratigraphic references. formation_id columns across our well, completion, and formation-top tables reference this registry, so a name like Wolfcamp means the same unit everywhere.", "tier": "public_aggregate", "singleton_schema": "formations", "primary_key": [ "formation_id" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "formation_id", "type": "string", "nullable": false, "description": "Stable unit identifier (opaque slug: treat as a key, don't parse it).", "enum": [] }, { "name": "canonical_name", "type": "string", "nullable": false, "description": "Canonical unit name (e.g. Wolfcamp, Bakken, Montney).", "enum": [] }, { "name": "rank", "type": "string", "nullable": false, "description": "Stratigraphic rank: `group`, `formation`, `member`, or `bed` per the North American stratigraphic code, plus `age` for time-tier buckets used when only a geological age is reported.\n", "enum": [ "group", "formation", "member", "bed", "age" ] }, { "name": "parent_formation_id", "type": "string", "nullable": true, "description": "The containing unit, where one exists (member to formation to group); NULL at the top of a hierarchy.\n", "enum": [] }, { "name": "strat_order_base", "type": "float64", "nullable": true, "description": "Older end of the unit's age range, in millions of years. For a named rock unit this is the base of the age range the name carries across its published usages (not a point age), so for a long-ranging or loosely defined name it can be considerably older than the unit is anywhere. For an age bucket (rank `age`) it is the start of that geological interval. Two units are reliably ordered by comparing these values only where their age ranges do not overlap. NULL where the source records no age. A published range is not always usable for ordering: see `strat_order_withheld_reason`.\n", "enum": [] }, { "name": "strat_order_top", "type": "float64", "nullable": true, "description": "Younger end of that same age range, in millions of years. For an age bucket (rank `age`) it is the end of that geological interval. Together with the older end it gives the unit's full age span: where two units' age ranges do not overlap, this pair of values orders them by age; where the ranges overlap, neither value orders them. NULL where the source records no age. A published range is not always usable for ordering: see `strat_order_withheld_reason`.\n", "enum": [] }, { "name": "strat_order_withheld_reason", "type": "string", "nullable": true, "description": "Why this unit's published age range must not be used to ORDER it against another unit. Normally empty, and the range then means what it says. `interval_label` means the source's only age for this unit is a bare geological-interval label (the start and end of a named period, carried unchanged) rather than a range measured from where the name has actually been mapped. The range is still shown, because it is the age the source records; we simply do not sequence rocks on it, since it cannot be told apart from a measured range and ordering on it silently places rocks in the wrong order.\n", "enum": [] }, { "name": "macrostrat_strat_name_id", "type": "int32", "nullable": true, "description": "Macrostrat stratigraphic-name id, where the unit is anchored there.", "enum": [] }, { "name": "macrostrat_concept_id", "type": "int32", "nullable": true, "description": "Macrostrat concept id, where available.", "enum": [] }, { "name": "geolex_unit_id", "type": "string", "nullable": true, "description": "USGS Geolex unit id (US units), where available.", "enum": [] }, { "name": "weblex_gscc_id", "type": "string", "nullable": true, "description": "Canadian WEBLEX / GSC lexicon id, where available.", "enum": [] }, { "name": "lithology", "type": "string", "nullable": true, "description": "Dominant lithology, where recorded (e.g. sandstone, limestone, shale).", "enum": [] }, { "name": "source", "type": "string", "nullable": false, "description": "Where the registry row came from: public stratigraphic databases or our own curation.\n", "enum": [] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "formations" ], "regions_live_names": [] }, "gold_organization_event_wells": { "description": "The specific wells covered by a scoped organization event. When an asset transfer moves only part of a company's assets, this holds the frozen set of wells the deal covered as of its effective date. Most events apply to whole organizations and need no well list, so this table is small and may be empty.", "tier": "portal", "singleton_schema": "organizations", "primary_key": [ "event_id", "well_id" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "event_id", "type": "string", "nullable": false, "description": "The scoped event (join to gold_organization_events).", "enum": [] }, { "name": "well_id", "type": "string", "nullable": false, "description": "A well covered by the event (join to gold_wells).", "enum": [] }, { "name": "source", "type": "string", "nullable": true, "description": "How the well entered the set: `curated` = hand-specified, `admin_filter` = selected by administrative attributes, `geometry` = selected by geographic footprint, `well_list` = imported from a published deal well list.\n", "enum": [ "curated", "admin_filter", "geometry", "well_list" ] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "organizations" ], "regions_live_names": [] }, "gold_organization_events": { "description": "Corporate events that change who owns or operates assets: acquisitions, mergers, name changes, scoped asset transfers, and identity corrections. One row per event with the organizations involved and the date it took effect. This drives ownership-over-time attribution: activity before the effective date stays with the original company, after it with the successor.", "tier": "public_aggregate", "singleton_schema": "organizations", "primary_key": [ "event_id" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "event_id", "type": "string", "nullable": false, "description": "Stable event identifier.", "enum": [] }, { "name": "event_type", "type": "string", "nullable": false, "description": "`acquisition` = the source organization was taken over by the target; `merger` = the source merged into the target; `name_change` = same entity renamed to the target; `asset_transfer` = a scoped set of assets changed hands (see gold_organization_event_wells for the wells); `entity_correction` = a registry identity fix rather than a real-world event; `subsidiary_acquisition` = the target acquired the source, which continues to operate under its own name.\n", "enum": [ "acquisition", "merger", "name_change", "asset_transfer", "entity_correction", "subsidiary_acquisition" ] }, { "name": "effective_date", "type": "date", "nullable": true, "description": "Date the change took effect.", "enum": [] }, { "name": "announced_date", "type": "date", "nullable": true, "description": "Announcement date, where known.", "enum": [] }, { "name": "source_org_id", "type": "string", "nullable": false, "description": "The organization the event happened to: the acquired, merging, or renamed party.\n", "enum": [] }, { "name": "target_org_id", "type": "string", "nullable": true, "description": "The counterparty or continuing entity: the acquirer, the merged-into company, or the new name.\n", "enum": [] }, { "name": "description", "type": "string", "nullable": true, "description": "Free-text summary of the event.", "enum": [] }, { "name": "source", "type": "string", "nullable": false, "description": "How the event record was created: `seed` = curated starting set, `enrichment` = automated research pipeline, `correction` = fix applied after the fact.\n", "enum": [ "seed", "enrichment", "correction" ] }, { "name": "effective_date_precision", "type": "string", "nullable": true, "description": "How precisely the effective date is known: `day` = exact date from a primary source; `month` or `year` = the date is pinned only to that month or year. The stored date is always the best-evidenced boundary we have: a lower precision widens the uncertainty around that date, it never shifts the date to the start of a month or year. Blank = not yet classified.\n", "enum": [ "day", "month", "year" ] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "organizations" ], "regions_live_names": [] }, "gold_organization_name_mappings": { "description": "How reported operator names resolve to organizations. Regulators publish the same company under many spellings; each row maps one normalized reported name, within one region, to its organization_id. This is the exact lookup our own attribution uses. Apply it to your raw data to get the same resolution.", "tier": "public_aggregate", "singleton_schema": "organizations", "primary_key": [ "normalized_name", "region" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "normalized_name", "type": "string", "nullable": false, "description": "Reported operator name after lookup normalization: uppercased, whitespace collapsed, the ampersand written as AND, trailing legal suffixes (INC, LLC, CO, ...) stripped, and a trailing period, comma or hyphen removed. Other punctuation from the source name is kept.\n", "enum": [] }, { "name": "region", "type": "string", "nullable": false, "description": "Region the mapping applies in (a region code such as `tx`), or `*` for a mapping valid across all regions.\n", "enum": [] }, { "name": "raw_example", "type": "string", "nullable": true, "description": "One example of a raw reported string behind this normalized name.", "enum": [] }, { "name": "organization_id", "type": "string", "nullable": false, "description": "The organization this name resolves to.", "enum": [] }, { "name": "source", "type": "string", "nullable": false, "description": "How the mapping was created: `seed` = curated starting set, `enrichment` = automated research pipeline, `correction` = fix applied after the fact.\n", "enum": [ "seed", "enrichment", "correction" ] }, { "name": "is_auto", "type": "boolean", "nullable": true, "description": "True when the mapping was produced by automated name matching rather than curation.\n", "enum": [] }, { "name": "created_date", "type": "date", "nullable": true, "description": "Date the mapping was added.", "enum": [] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "organizations" ], "regions_live_names": [] }, "gold_organization_registrations": { "description": "The bridge between regulator-issued operator IDs (Texas P-5, New Mexico OGRID, and each region's equivalent) and our canonical company register: normally one row per (region, registration ID), carrying the name as registered, registration status, role flags (operator / gatherer / midstream), and headquarters as filed. organization_id links to gold_organizations once the operator is resolved. Where the company behind an ID was renamed, the ID carries one row per period instead (see valid_from / valid_to) so that filings made before and after the rename are attributed to the right company.", "tier": "public_aggregate", "primary_key": [ "region", "registration_id", "valid_from" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "region", "type": "string", "nullable": false, "description": "Region code the registration belongs to (e.g. tx, nm, ab, brazil). First part of the primary key.\n", "enum": [] }, { "name": "registration_id", "type": "string", "nullable": false, "description": "The regulator's identifier for this entity in this region: TX P-5 number, NM OGRID, PA OGO number, AB AER licensee number, Brazil ANP CNPJ. Second part of the primary key. Opaque string. Do not parse.\n", "enum": [] }, { "name": "organization_id", "type": "string", "nullable": true, "description": "Join key to the company register (gold_organizations). NULL when this registration has not yet been resolved to a canonical organization (typical for newly registered or rarely active operators); resolved coverage grows over time.\n", "enum": [] }, { "name": "link_source", "type": "string", "nullable": true, "description": "How the organization_id link was established: 'write_initial' (resolved from name research at a bridge build), 'relink_from_mapping' (backfilled by the automatic re-link pass on a name match), 'manual_split' / 's1-verified' / 'merge_redirect' (manual adjudications: these survive rebuilds unconditionally), 'derived_window' (period row minted for a renamed company; see valid_from/valid_to), 'manual_unlink' (an adjudicated DETACHMENT: the registration's identity was ruled uncertain, so organization_id is NULL by decision; survives rebuilds and is never auto-refilled). Stable across rebuilds while the link itself is unchanged. NULL when organization_id is NULL, except an adjudicated detachment: 'manual_unlink' is the value written for one; a manual adjudication value beside a NULL organization_id reads the same way.\n", "enum": [] }, { "name": "linked_at", "type": "date", "nullable": true, "description": "Date the organization_id link was first established. NULL when organization_id is NULL; on an adjudicated detachment it is NULL or the detachment's own stamp date. Stable. Use it to audit when a regulator ID was linked to a canonical organization.\n", "enum": [] }, { "name": "registered_name", "type": "string", "nullable": false, "description": "Entity name as filed with the regulator. May differ between regions for the same canonical organization (e.g. \"APACHE CORPORATION\" vs \"APACHE CORP-DELAWARE LP\").\n", "enum": [] }, { "name": "status", "type": "string", "nullable": true, "description": "Regulator-side status: active = currently registered and can hold permits; inactive = registered but not active; delinquent = registered and holding property or activity, but not in good standing because a required filing lapsed: the regulator will not issue new permits until it refiles; dissolved = terminated; unknown = the source gives no readable status.\n", "enum": [ "active", "inactive", "dissolved", "delinquent", "unknown" ] }, { "name": "status_effective_date", "type": "date", "nullable": true, "description": "When the current status took effect, when known. NULL if not provided.\n", "enum": [] }, { "name": "is_operator", "type": "boolean", "nullable": true, "description": "Registered as an oil & gas operator in this region. NULL where the regulator's register covers more than operators and publishes no role dimension: the regulator says nothing either way, which is not the same as saying the company is not an operator.\n", "enum": [] }, { "name": "is_gatherer", "type": "boolean", "nullable": true, "description": "Registered as a gatherer/transporter (gas or oil pipeline gathering). Not all regulators distinguish; false where the source has no signal. So, unlike is_operator, false here does not necessarily mean the regulator said no.\n", "enum": [] }, { "name": "is_midstream", "type": "boolean", "nullable": true, "description": "Registered as a midstream company (processing, storage, transmission). Often overlaps with is_gatherer where the regulator treats them as one role.\n", "enum": [] }, { "name": "hq_address_line1", "type": "string", "nullable": true, "description": "Headquarters street address as filed with the regulator.\n", "enum": [] }, { "name": "hq_address_city", "type": "string", "nullable": true, "description": "Headquarters city as filed.\n", "enum": [] }, { "name": "hq_address_state_province", "type": "string", "nullable": true, "description": "Headquarters state or province as filed.\n", "enum": [] }, { "name": "hq_address_country", "type": "string", "nullable": true, "description": "Headquarters country (ISO code or regulator-provided string): as filed where the register carries an address; where it carries none, the licensing jurisdiction's country may be carried as a documented default.\n", "enum": [] }, { "name": "hq_address_zip", "type": "string", "nullable": true, "description": "Headquarters postal code as filed.\n", "enum": [] }, { "name": "delisted_date", "type": "date", "nullable": true, "description": "Date this registration was first observed absent from the regulator's register. The row is kept so its history survives the delisting. NULL = present in the latest register. Stays at the first observed absence across repeat cycles, and clears automatically if the registration reappears. When non-NULL, the as-filed fields (registered_name, status, roles, address) are a last-known snapshot as of this date: treat them as historical, not live.\n", "enum": [] }, { "name": "valid_from", "type": "date", "nullable": true, "description": "Start of the period this registration id referred to this company. Blank means from the beginning of its observed life. Set only where the company behind the id was renamed, so that production filed before and after the rename is attributed to the right name.\n", "enum": [] }, { "name": "valid_to", "type": "date", "nullable": true, "description": "End of the period this registration id referred to this company. Blank means up to the present. Set only where the company behind the id was renamed.\n", "enum": [] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "ab", "ak", "al", "ar", "argentina", "bc", "brazil", "ca", "co", "gom", "ks", "la", "mb", "mi", "mt", "nm", "oh", "ok", "pa", "pacific", "sk", "tx", "ut", "wv", "wy" ], "regions_live_names": [ "Alberta", "Alaska", "Alabama", "Arkansas", "Argentina", "British Columbia", "Brazil", "California", "Colorado", "Gulf of Mexico", "Kansas", "Louisiana", "Manitoba", "Michigan", "Montana", "New Mexico", "Ohio", "Oklahoma", "Pennsylvania", "Pacific OCS", "Saskatchewan", "Texas", "Utah", "West Virginia", "Wyoming" ] }, "gold_organizations": { "description": "Master register of the companies behind the wells: operators, service companies, midstream, integrated and downstream groups. One row per organization, deduplicated across regions and name variants; operator id columns across the well, production, and permit tables reference it by organization_id. Where a company was acquired, merged, or renamed, successor_id points to the organization that carries on.", "tier": "public_aggregate", "singleton_schema": "organizations", "primary_key": [ "organization_id" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "organization_id", "type": "string", "nullable": false, "description": "Stable organization identifier (opaque slug). Operator id columns across our tables join to this.\n", "enum": [] }, { "name": "name", "type": "string", "nullable": false, "description": "Canonical organization name.", "enum": [] }, { "name": "short_name", "type": "string", "nullable": true, "description": "Shorter display name, where one is in common use.", "enum": [] }, { "name": "organization_type", "type": "string", "nullable": false, "description": "Kind of business. `e_and_p` = exploration & production (well operators); `integrated` = majors spanning upstream to downstream; `placeholder` = internal bucket for unattributable operators rather than a real company.\n", "enum": [ "e_and_p", "integrated", "downstream", "midstream", "service", "government", "power_generation", "placeholder", "other" ] }, { "name": "is_public", "type": "boolean", "nullable": true, "description": "True when the organization is publicly listed; NULL where not yet researched.", "enum": [] }, { "name": "ticker", "type": "string", "nullable": true, "description": "Stock ticker, for public companies.", "enum": [] }, { "name": "exchange", "type": "string", "nullable": true, "description": "Listing exchange, for public companies.", "enum": [] }, { "name": "website", "type": "string", "nullable": true, "description": "Company website.", "enum": [] }, { "name": "country", "type": "string", "nullable": true, "description": "Country of registration or head office (ISO 3166-1 alpha-2).", "enum": [] }, { "name": "state_province", "type": "string", "nullable": true, "description": "Head-office state or province, where known.", "enum": [] }, { "name": "status", "type": "string", "nullable": false, "description": "Lifecycle status. `inactive` = dormant but still extant; `acquired`, `merged`, and `renamed` mean the entity ended in that event: follow successor_id to the continuing organization; `unknown` = not yet researched.\n", "enum": [ "active", "inactive", "acquired", "merged", "dissolved", "renamed", "unknown" ] }, { "name": "successor_id", "type": "string", "nullable": true, "description": "For acquired, merged, or renamed organizations: the organization_id that carries on. Follow the chain to reach the current entity.\n", "enum": [] }, { "name": "successor_effective_date", "type": "date", "nullable": true, "description": "Date the succession took effect.", "enum": [] }, { "name": "parent_organization_id", "type": "string", "nullable": true, "description": "The organization this one rolls up to for company-level totals: a parent or holding company. Node identity is unchanged: production stays attributed to the operating entity. NULL where no parent is recorded: the company may be independent, not yet researched, or part of an affiliate group that has no holding company, so NULL does not mean independent.\n", "enum": [] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "organizations" ], "regions_live_names": [] }, "gold_producing_units": { "description": "The register of producing units coarser than a single well (an FPSO, an oil-sands project, a field, or a whole country), used where a source reports production at that level rather than per well. Each unit carries its grain, jurisdiction, and operator. Volumes live in gold_unit_production; the gold.production view unifies well-grain and unit-grain series into one all-grain read surface.", "tier": "portal", "primary_key": [ "producing_unit_id" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "producing_unit_id", "type": "string", "nullable": false, "description": "Globally unique producing-unit identifier (opaque string), this table's primary key. Never parse substrings out of it. This register stores only units coarser than a well; in the unified gold.production view, well-grain series carry the well's well_id in this role.\n", "enum": [] }, { "name": "grain", "type": "string", "nullable": false, "description": "The unit's metering grain, the level at which its production is reported: facility (e.g. an FPSO), project (e.g. an oil-sands mine), field, lease (a regulator lease/unit reporting entity), block (a licensed concession/exploitation block), operator (one operator's whole reported portfolio in a jurisdiction, where the source publishes no finer split), state (a state-level series where no finer source exists), or country. Wells are never stored in this register; the unified gold.production view carries grain 'well' for well-grain series.\n", "enum": [ "facility", "project", "field", "lease", "block", "operator", "state", "country" ] }, { "name": "name", "type": "string", "nullable": false, "description": "Human-readable unit name (e.g. \"Liza Unity\", \"Guyana\"). Casing follows the publishing source (some regulators publish upper-case names, others title-case), and names are not unique: unit_id is the key, and the same name can appear in more than one country or casing. Compare or de-duplicate names case-insensitively.\n", "enum": [] }, { "name": "country", "type": "string", "nullable": false, "description": "Country code (ISO 3166-1 alpha-2, upper-case, e.g. GY).\n", "enum": [] }, { "name": "region", "type": "string", "nullable": true, "description": "State, province, or sub-national area where applicable; NULL for supra-regional or national units (e.g. a country-grain row).\n", "enum": [] }, { "name": "parent_unit_id", "type": "string", "nullable": true, "description": "The unit's parent in the roll-up hierarchy, e.g. a facility points at its country roll-up unit; the country unit has NULL (top). The hierarchy is ragged rather than a fixed tree (one FPSO can serve many fields). Production is never double-counted along this chain: no unit carries production while an ancestor also does. The chain follows how volumes are actually reported and aggregated, which is not always the same as licensing or concession geography: where a regulator meters a field into a different block than the concession catalogue lists it under, the parent shown here is the one whose reported volumes contain it.\n", "enum": [] }, { "name": "operator", "type": "string", "nullable": true, "description": "The company operating this unit today, as a canonical company name: one current value per unit, with mergers and acquisitions applied as of today. May lag a recent transfer, because it is taken from the latest operator on file. For the operator during a particular month, read operator on gold_unit_production, which carries the owner at that month. NULL when unresolved, or where no operator applies at this unit's grain (e.g. state or national roll-ups).\n", "enum": [] }, { "name": "operator_id", "type": "string", "nullable": true, "description": "Stable company identifier for operator: the owner as of today. Join key to the organizations register (gold_organizations). NULL when the operator name cannot be resolved to a registered organization, or where no operator applies at this grain.\n", "enum": [] }, { "name": "latitude", "type": "float64", "nullable": true, "description": "Representative point for the unit (WGS84), e.g. an FPSO's mooring location. NULL where no single representative point applies (e.g. a country unit).\n", "enum": [] }, { "name": "longitude", "type": "float64", "nullable": true, "description": "Representative point longitude (WGS84). Sourced as a pair with latitude.\n", "enum": [] } ], "regional_columns": [], "region_extras": { "eia": [ { "name": "source", "type": "string", "description": "Who reported these volumes. `eia` for this container: the U.S. Energy Information Administration, whose state-level series covers producing states that publish no well-level data of their own.\n" } ], "eia_intl": [ { "name": "source", "type": "string", "description": "Who reported these volumes. `eia` for this container: the U.S. Energy Information Administration, whose International Energy Statistics cover producing countries that publish no well-level data of their own.\n" } ], "mexico": [ { "name": "campo_sih", "type": "string", "description": "" }, { "name": "ubicacion", "type": "string", "description": "" } ] }, "serving_derived": [], "data_currency": [], "regions_live": [ "ab", "colombia", "ecuador", "eia", "eia_intl", "guyana", "mexico", "nl_offshore", "ok" ], "regions_live_names": [ "Alberta", "Colombia", "Ecuador", "US state totals (EIA)", "Americas country totals (EIA)", "Guyana", "Mexico", "Newfoundland & Labrador Offshore", "Oklahoma" ] }, "gold_rig_activity": { "description": "Active drilling-rig counts, a leading indicator of upcoming supply. Parallel series from independent published sources, each at its native breakdown: the Baker Hughes weekly North America count and Mexico's monthly regulator series. Series are never mixed or reconciled, so each row matches the figure its source publishes. Where a source does not break down an axis, that column carries `all`: aggregate only within one source and one period type.", "tier": "public_aggregate", "singleton_schema": "activity", "primary_key": [ "source", "date", "country", "state_province_code", "area", "basin", "environment", "rig_purpose", "target", "trajectory", "operator" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "source", "type": "string", "nullable": false, "description": "Which published series the row belongs to. Never sum across sources: they are independent measurements of rig activity.\n", "enum": [ "sih", "bakerhughes" ] }, { "name": "date", "type": "date", "nullable": false, "description": "Start date of the period the count covers.", "enum": [] }, { "name": "period", "type": "string", "nullable": false, "description": "Reporting cadence of the series: `month` or `week`. Don't mix cadences when aggregating.\n", "enum": [ "month", "week" ] }, { "name": "period_end_date", "type": "date", "nullable": false, "description": "The date the reported period runs to: for weekly series the source's own week-ending date (holiday weeks shift it earlier in the week), for monthly series the last day of the month. The date column carries the period's start.\n", "enum": [] }, { "name": "country", "type": "string", "nullable": false, "description": "Country (ISO 3166-1 alpha-2).", "enum": [] }, { "name": "state_province_code", "type": "string", "nullable": false, "description": "State or province code; `unassigned` where the source declines to place a rig in any state or province; `all` where the source doesn't split by state.\n", "enum": [] }, { "name": "state_province", "type": "string", "nullable": false, "description": "State or province name as the source publishes it; `unassigned` where the source declines to place a rig in any state or province; `all` where the source doesn't split by state.\n", "enum": [] }, { "name": "area", "type": "string", "nullable": false, "description": "The source's own sub-state area label (US county, Canadian sub-province area); `unassigned` where the source declines to place a rig; `all` where not broken down.\n", "enum": [] }, { "name": "basin", "type": "string", "nullable": false, "description": "Source-reported basin, or `all` where not split.", "enum": [] }, { "name": "environment", "type": "string", "nullable": false, "description": "Operating environment: onshore, offshore water-depth bands, or inland waters; `all` where not split.\n", "enum": [ "onshore", "offshore", "offshore_shallow", "offshore_deep", "offshore_ultra_deep", "inland_waters", "all" ] }, { "name": "rig_purpose", "type": "string", "nullable": false, "description": "Purpose of drilling: `development`, `exploration`, `appraisal`; `all` where not split.", "enum": [ "development", "exploration", "appraisal", "all" ] }, { "name": "target", "type": "string", "nullable": false, "description": "Target hydrocarbon: `oil`, `gas`, or `misc`; `all` where not split.", "enum": [ "oil", "gas", "misc", "all" ] }, { "name": "trajectory", "type": "string", "nullable": false, "description": "Wellbore trajectory: `horizontal`, `directional`, `vertical`, the source's own `other` residual bucket; `all` where not split.\n", "enum": [ "horizontal", "directional", "vertical", "other", "all" ] }, { "name": "operator", "type": "string", "nullable": false, "description": "Operator name where the source splits by operator (the Mexico series does); `all` otherwise.\n", "enum": [] }, { "name": "operator_id", "type": "string", "nullable": true, "description": "Our organization id for the operator, where resolvable; NULL otherwise.", "enum": [] }, { "name": "active_rigs", "type": "float64", "nullable": false, "description": "Average active rigs over the period, as reported by the source. Monthly averages can be fractional.\n", "enum": [] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "activity" ], "regions_live_names": [] }, "gold_unit_disposition": { "description": "Monthly gas and oil disposition for producing units coarser than a single well (an FPSO, a project, a field, or a whole country), one row per unit per month. This is the companion of the well-grain disposition table for sources that report at coarser grain: where the produced volume went, split into sold, flared, vented, reinjected, and fuel. The unit's name, grain, and jurisdiction live on the producing-units register (gold_producing_units); join monthly unit production for the produced denominator. NULL means the source didn't report that split; 0 is a reported zero. Each disposition column carries its own paired _origin column.", "tier": "portal", "primary_key": [ "producing_unit_id", "date" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "producing_unit_id", "type": "string", "nullable": false, "description": "Producing-unit identifier (opaque string, e.g. gy:stabroek:facility:liza-unity): the join key to gold_producing_units, which carries the unit's name, grain, and jurisdiction. Join monthly unit production on (producing_unit_id, date), restricted to its monthly rows, to compare disposition against produced volumes. Never parse substrings out of it.\n", "enum": [] }, { "name": "date", "type": "date", "nullable": false, "description": "Disposition month, always the first day of the month, matching monthly unit production. Sources that publish daily series are aggregated to the month, and a month the source covered only partially is withheld rather than published as if complete.\n", "enum": [] }, { "name": "gas_sold", "type": "int64", "nullable": true, "description": "Marketed/delivered gas in MCF: gas sold off the unit to a gatherer or purchaser. Within a month, sold can lag produced (tank and line-pack stock), so reconcile sold against produced cumulatively, not month by month; the gap between gross produced gas and this column is what you see comparing our gross series to marketed-gas series such as EIA's. NULL = the source did not report sold separately.\n", "enum": [] }, { "name": "gas_flared", "type": "int64", "nullable": true, "description": "Gas burned (flared) at the unit, in MCF. Kept separate from gas_vented because the split matters for emissions analysis (vented methane is far more potent than flared CO2). A source that reports only a combined figure populates gas_flared_vented instead, never a lossy split. NULL = not reported separately.\n", "enum": [] }, { "name": "gas_vented", "type": "int64", "nullable": true, "description": "Gas released unburned (vented) at the unit, in MCF. NULL = not reported separately.\n", "enum": [] }, { "name": "gas_flared_vented", "type": "int64", "nullable": true, "description": "Combined flared plus vented gas in MCF, for sources that report the two under a single code and cannot split them. A source that reports the split populates gas_flared and gas_vented and keeps this NULL; a source that reports only the combined figure populates this and keeps the split columns NULL, never a lossy split into one of them. NULL = no combined figure reported.\n", "enum": [] }, { "name": "gas_reinjected", "type": "int64", "nullable": true, "description": "Gas reinjected for pressure maintenance, cycling, gas lift, or enhanced recovery, in MCF. Dominant offshore, where associated gas is reinjected rather than exported, a major reason marketed gas runs far below gross. Can exceed the unit's own produced gas (recycled gas lift, purchased makeup gas), so exclude it when balancing sold against produced.\n", "enum": [] }, { "name": "gas_lease_fuel", "type": "int64", "nullable": true, "description": "Gas consumed at the unit as fuel (engines, heaters, compressors, and on an offshore facility the power generation and turbines), in MCF.\n", "enum": [] }, { "name": "gas_plant_fuel", "type": "int64", "nullable": true, "description": "Gas consumed as fuel at the processing plant, in MCF. Sparse, populated only where the source natively reports it.\n", "enum": [] }, { "name": "oil_sold", "type": "int64", "nullable": true, "description": "Marketed/sold oil plus condensate, in BBL. Only the sold split is carried for oil: other oil disposition (unit use, tank stock change) is noise at monthly grain. Oil includes condensate, matching monthly unit production.\n", "enum": [] }, { "name": "gas_sold_origin", "type": "string", "nullable": true, "description": "How gas_sold was derived: reported = the source reported this value at this unit's grain; lease_allocated = the source reported it at a coarser grain and we split it down using the same allocation weights as monthly production, so values roll up exactly to the coarser total. NULL exactly when gas_sold is NULL.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "gas_flared_origin", "type": "string", "nullable": true, "description": "How gas_flared was derived: same values as gas_sold_origin. NULL exactly when gas_flared is NULL.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "gas_vented_origin", "type": "string", "nullable": true, "description": "How gas_vented was derived: same values as gas_sold_origin. NULL exactly when gas_vented is NULL.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "gas_flared_vented_origin", "type": "string", "nullable": true, "description": "How gas_flared_vented was derived: same values as gas_sold_origin. NULL exactly when gas_flared_vented is NULL.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "gas_reinjected_origin", "type": "string", "nullable": true, "description": "How gas_reinjected was derived: same values as gas_sold_origin. NULL exactly when gas_reinjected is NULL.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "gas_lease_fuel_origin", "type": "string", "nullable": true, "description": "How gas_lease_fuel was derived: same values as gas_sold_origin. NULL exactly when gas_lease_fuel is NULL.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "gas_plant_fuel_origin", "type": "string", "nullable": true, "description": "How gas_plant_fuel was derived: same values as gas_sold_origin. NULL exactly when gas_plant_fuel is NULL.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "oil_sold_origin", "type": "string", "nullable": true, "description": "How oil_sold was derived: same values as gas_sold_origin. NULL exactly when oil_sold is NULL.\n", "enum": [ "reported", "lease_allocated" ] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "guyana" ], "regions_live_names": [ "Guyana" ] }, "gold_unit_production": { "description": "Monthly production volumes for producing units coarser than a single well (an FPSO, a project, a field, or a whole country), one row per unit per month. This is the companion of the well-grain production table for sources that report at coarser grain; the unit's name, grain, and jurisdiction live on the producing-units register (gold_producing_units). A volume is NULL when that stream isn't reported at this unit's grain (e.g. gas metered nationally while oil is per-facility): NULL means no series at this grain, never zero. The gold.production view unifies this table with well-grain production into one all-grain surface.", "tier": "portal", "primary_key": [ "producing_unit_id", "date", "period_days" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "producing_unit_id", "type": "string", "nullable": false, "description": "Producing-unit identifier (opaque string, e.g. gy:stabroek:facility:liza-unity): the join key to gold_producing_units, which carries the unit's name, grain, and jurisdiction. Never parse substrings out of it.\n", "enum": [] }, { "name": "date", "type": "date", "nullable": false, "description": "Production month, always the first day of the month. Sources that publish daily series are aggregated to the month.\n", "enum": [] }, { "name": "oil_per_month", "type": "int64", "nullable": true, "description": "Oil produced during the month, in barrels (BBL), including condensate. NULL when this unit has no oil series at its grain (e.g. a national roll-up carrying only gas): NULL means not reported at this grain, never zero.\n", "enum": [] }, { "name": "gas_per_month", "type": "int64", "nullable": true, "description": "Natural gas produced during the month, in thousand cubic feet (MCF). NULL when this unit has no gas series at its grain (e.g. an FPSO whose gas is metered only nationally): NULL is not zero; we never fabricate a split the source doesn't report.\n", "enum": [] }, { "name": "water_per_month", "type": "int64", "nullable": true, "description": "Water produced during the month, in barrels (BBL). NULL where the grain has no water series.\n", "enum": [] }, { "name": "producing_days", "type": "int16", "nullable": true, "description": "Days the unit actually produced during this period, as reported by the source. Usually NULL for coarse grains: facility and national series rarely report it. Distinct from period_days (the calendar length of the period): producing_days counts days WITH production.\n", "enum": [] }, { "name": "period_days", "type": "int16", "nullable": false, "description": "Calendar length of this row's reporting period, in days: 28-31 for a monthly row, 365 or 366 for an annual one (some agency series report gas only per year). Always derived from the row's own period, so leap years are exact. Divide a volume by this for a daily rate.\n", "enum": [] }, { "name": "operator", "type": "string", "nullable": true, "description": "Company operating this unit during this month, ownership changes (M&A) applied as of this month. For units whose source publishes no per-month operator, populated only where the operator is genuinely constant over the stored span, or inherited from the containing unit (e.g. a field inherits its block's operator); NULL where no operator applies at this grain (e.g. state or national roll-ups).\n", "enum": [] }, { "name": "operator_id", "type": "string", "nullable": true, "description": "Stable company identifier for operator: the owner at this month. Join key to the organizations register. NULL when the operator name does not resolve or no operator applies at this grain.\n", "enum": [] }, { "name": "reported_operator", "type": "string", "nullable": true, "description": "The operator exactly as the regulatory source records it for this unit and month, resolved to a company (no merger succession applied). NULL where the source publishes no operator at this unit's grain.\n", "enum": [] }, { "name": "reported_operator_id", "type": "string", "nullable": true, "description": "Stable company identifier for reported_operator (no merger succession). NULL wherever reported_operator is NULL (see there), and additionally where a published name is not yet mapped to a registered organization, so a NULL id beside a populated reported_operator_entity means an unmapped name, not a missing operator.\n", "enum": [] }, { "name": "reported_operator_entity", "type": "string", "nullable": true, "description": "The operator name exactly as printed by the source for this unit and month, before any cleaning or resolution. NULL where the source publishes no operator at this grain: a populated operator beside a NULL reported_operator_entity means the value was inherited or curated, not printed by the source.\n", "enum": [] }, { "name": "reported_operator_registration_id", "type": "string", "nullable": true, "description": "The regulator's own company registration id as printed by the source for this unit and month (e.g. Oklahoma OTC company number), passed through raw. NULL otherwise.\n", "enum": [] }, { "name": "record_origin", "type": "string", "nullable": false, "description": "How this row was derived: the same provenance vocabulary as well-grain production (reported, gap_filled, lease_allocated, period_allocated, reconciled, wellstar_estimated, source_corrupt). Coarse-grain unit rows are typically reported.\n", "enum": [ "reported", "gap_filled", "lease_allocated", "period_allocated", "reconciled", "wellstar_estimated", "source_corrupt" ] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [ { "region": "mexico", "region_name": "Mexico", "as_of": "1999-12-01", "customer_note": "Mexican production from 2000 onward is published per well in the well production table, not here. This field-level series covers the years before that." } ], "regions_live": [ "ab", "colombia", "ecuador", "eia", "eia_intl", "guyana", "mexico", "nl_offshore", "ok" ], "regions_live_names": [ "Alberta", "Colombia", "Ecuador", "US state totals (EIA)", "Americas country totals (EIA)", "Guyana", "Mexico", "Newfoundland & Labrador Offshore", "Oklahoma" ] }, "gold_well_completions": { "description": "One row per completion event (the initial completion and each later recompletion) as filed with the regulator. Carries the completion date, the wellbore configuration produced by the event (formation, depths, lateral length, trajectory), and interval details. Plug-and-abandon events are not completions; they live on the well register (plugged_date).", "tier": "portal", "primary_key": [ "completion_id" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "completion_id", "type": "string", "nullable": false, "description": "Globally unique completion identifier (opaque string) - this table's primary key. Never parse substrings out of it.\n", "enum": [] }, { "name": "well_id", "type": "string", "nullable": false, "description": "Join key to the well register. Always populated.\n", "enum": [] }, { "name": "completion_date", "type": "date", "nullable": true, "description": "Date this completion was finalized per the regulatory filing. Every row is a completion - plug-and-abandon events are not in this table. Where a source dates completions at well grain rather than per event (Wyoming; most Ohio rows), every completion row of a well carries the well's date - real well-level information, but it does not order that well's completions.\n", "enum": [] }, { "name": "event_type", "type": "string", "nullable": true, "description": "The kind of completion event: initial_completion (the well's first completion on record) or recompletion (a later completion of the same well). Classified from the source's own event typing or sequence numbering where published, else from completion-date order. NULL where the records carry no order evidence for the event (an undated completion among others), so first-vs-later is unknown. A well can carry more than one initial_completion where the source records the first completion as several records - dual completions, or the perforation intervals of one job. A well whose record set contains exactly one completion is labeled initial_completion on that single-record basis alone. Where a source publishes no per-completion dates or event typing (Wyoming today), that is the only basis in use: every labeled row there is a single-record well, and multi-record wells are NULL.\n", "enum": [ "initial_completion", "recompletion" ] }, { "name": "operator", "type": "string", "nullable": true, "description": "The operator responsible for this completion, as a canonical company name. Where the source's completion record names an operator, this is the operator at the time of the completion - a point-in-time fact. Where it does not (many regulators publish completion records without an operator), we carry the well's current operator of record instead. This table carries the name only; for a stable company identifier, join the well register via well_id, or resolve the raw operator_entity through the organization name mappings. (This styled display is an output - it is not guaranteed to normalize back to a mapping key.)\n", "enum": [] }, { "name": "operator_entity", "type": "string", "nullable": true, "description": "Raw filing entity name from the source - a historical fact, preserved without normalization.\n", "enum": [] }, { "name": "trajectory", "type": "string", "nullable": true, "description": "Wellbore trajectory produced by this completion: horizontal, vertical, or directional. NULL = not available.\n", "enum": [ "horizontal", "vertical", "directional" ] }, { "name": "formation", "type": "string", "nullable": true, "description": "Best-available target/producing formation. formation_method, where populated, records how the value was determined (reported = from the operator's filing). The value is normalized to the same canonical vocabulary as the well register where the region's formation mapping covers it; elsewhere it is carried as the source publishes it.\n", "enum": [] }, { "name": "zone", "type": "string", "nullable": true, "description": "Landing zone within the formation - a named bench or sand, e.g. Middle Bakken. Derived from the operator's reported formation, pool, or sand naming in the source data; for North Dakota, extracted from the narrative text of the well file. Same zone vocabulary as the well register.\n", "enum": [] }, { "name": "formation_reported", "type": "string", "nullable": true, "description": "Raw reported formation from the completion filing (uppercased, trimmed) - the original filing text before normalization, always preserved. Where the well filed a formation or pool code rather than a name, this is the source's own register label for that code, verbatim. Populated even when formation is NULL.\n", "enum": [] }, { "name": "formation_method", "type": "string", "nullable": true, "description": "How the formation value was determined: reported = derived from source-reported formation or pool information (normalization, decoding, or selection between reported values may apply); survey = directional-survey-based placement; modeled = filled from the formation surface model; stratigraphic_pick = assigned from the deepest published stratigraphic pick on this wellbore - a third-party geological-survey pick rather than an operator declaration, and an estimate of the deepest formation penetrated rather than a declared target or producing formation.\n", "enum": [ "reported", "survey", "modeled", "stratigraphic_pick" ] }, { "name": "tvd", "type": "int32", "nullable": true, "description": "True vertical depth to the producing zone, in feet.\n", "enum": [] }, { "name": "md", "type": "int32", "nullable": true, "description": "Total measured depth, surface to total depth, in feet.\n", "enum": [] }, { "name": "lateral_length", "type": "int32", "nullable": true, "description": "Lateral length in feet for this completion. Usually the completed or perforated interval, but not always: where the completion record carries no interval the value is the drilled lateral measured along a directional survey or along the mapped wellbore path, or a geometric estimate of it (straight-line heel-to-toe or surface-to-bottom-hole distance, or measured depth minus vertical depth). lateral_length_source says which. NULL for vertical wells.\n", "enum": [] }, { "name": "lateral_length_source", "type": "string", "nullable": true, "description": "How lateral_length was determined: perf_interval = the perforated interval (preferred); treatment = the stimulated interval; survey = the directional survey's along-hole length; wellpath_polyline = the length of the mapped wellbore path; heel_toe_geodesic = the straight-line distance between the lateral's heel and toe; surface_bhl_geodesic = the straight-line distance from surface to bottom hole, less a region-calibrated build-section correction where one exists (uncorrected it includes the build-section step-out); operator_reported = a single reported length; md_minus_tvd = measured depth minus vertical depth - a crude estimate and the lowest-confidence tier.\n", "enum": [ "perf_interval", "treatment", "survey", "wellpath_polyline", "heel_toe_geodesic", "surface_bhl_geodesic", "operator_reported", "md_minus_tvd" ] }, { "name": "perf_top", "type": "int32", "nullable": true, "description": "Top of the perforated interval, in feet measured depth.\n", "enum": [] }, { "name": "perf_bottom", "type": "int32", "nullable": true, "description": "Bottom of the perforated interval, in feet measured depth.\n", "enum": [] }, { "name": "hydraulic_fracking_used", "type": "boolean", "nullable": true, "description": "Whether any hydraulic fracturing was used, including conventional small frac jobs. Three-valued: TRUE = a frac is recorded (the frac records carry the treatment detail); FALSE = confirmed not fracked - asserted only where the regulator's own filing says so: the operator answered no to the completion report's hydraulic-fracturing question (e.g. TX), or a mandatory frac/stimulation register records no treatment (e.g. WY, OH); NULL = unknown (voluntary or incomplete reporting, e.g. FracFocus-only regions). NULL is never \"not fracked\".\n", "enum": [] } ], "regional_columns": [], "region_extras": { "ar": [ { "name": "ar_well_key", "type": "string", "description": "" }, { "name": "wellbore_type", "type": "string", "description": "" }, { "name": "wellbore_status", "type": "string", "description": "" }, { "name": "completion_type", "type": "string", "description": "" }, { "name": "field", "type": "string", "description": "" }, { "name": "permit_number", "type": "string", "description": "" } ], "bc": [ { "name": "wa_number", "type": "string", "description": "" }, { "name": "completion_event_seq", "type": "string", "description": "" } ], "co": [ { "name": "formation_code", "type": "string", "description": "" }, { "name": "sidetrack", "type": "string", "description": "" } ], "la": [ { "name": "la_well_serial", "type": "string", "description": "" } ], "nd": [ { "name": "file_no", "type": "int64", "description": "" }, { "name": "source", "type": "string", "description": "" } ], "nm": [ { "name": "pool_idn", "type": "int64", "description": "" }, { "name": "pool_name", "type": "string", "description": "" }, { "name": "bhl_latitude", "type": "float64", "description": "" }, { "name": "bhl_longitude", "type": "float64", "description": "" } ], "ok": [ { "name": "bhl_latitude", "type": "float64", "description": "" }, { "name": "bhl_longitude", "type": "float64", "description": "" }, { "name": "completion_no", "type": "int32", "description": "" } ], "pa": [ { "name": "unconventional", "type": "boolean", "description": "" } ], "tx": [ { "name": "district", "type": "string", "description": "" }, { "name": "county", "type": "string", "description": "" }, { "name": "field_name", "type": "string", "description": "" }, { "name": "well_type", "type": "string", "description": "" }, { "name": "operator_no", "type": "string", "description": "" }, { "name": "plug_back_depth_tvd", "type": "int32", "description": "" }, { "name": "plug_back_depth_md", "type": "int32", "description": "" }, { "name": "is_multiple_completion", "type": "boolean", "description": "" }, { "name": "commingled", "type": "boolean", "description": "" }, { "name": "latest_completion_date", "type": "date", "description": "" }, { "name": "n_reports", "type": "int32", "description": "" }, { "name": "n_intervals", "type": "int32", "description": "" } ] }, "serving_derived": [], "data_currency": [], "regions_live": [ "ak", "ar", "argentina", "bc", "co", "la", "mt", "nd", "nm", "oh", "ok", "pa", "tx", "ut", "wv", "wy" ], "regions_live_names": [ "Alaska", "Arkansas", "Argentina", "British Columbia", "Colorado", "Louisiana", "Montana", "North Dakota", "New Mexico", "Ohio", "Oklahoma", "Pennsylvania", "Texas", "Utah", "West Virginia", "Wyoming" ] }, "gold_well_disposition": { "description": "Monthly gas and oil disposition per well: where the produced volume went (sold, flared, vented, reinjected, used as lease or plant fuel), one row per well per month. NULL means the source didn't report that split; 0 is a reported zero. Each disposition column carries its own paired _origin column (reported at well grain vs allocated from lease-level filings). Together with monthly production this gives gross-to-marketed reconciliation and flaring intensity at well grain.", "tier": "portal", "primary_key": [ "well_id", "date" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "well_id", "type": "string", "nullable": false, "description": "Join key to the well register. Always populated. Same well-month grain as the monthly production series; join on (well_id, date) to compare disposition against produced volumes.\n", "enum": [] }, { "name": "date", "type": "date", "nullable": false, "description": "Disposition month, always the first day of the month, matching the production series.\n", "enum": [] }, { "name": "year", "type": "int16", "nullable": false, "description": "Calendar year of the disposition month (equals the year of date). Provided for fast year-level filtering and partition pruning.\n", "enum": [] }, { "name": "gas_sold", "type": "int32", "nullable": true, "description": "Marketed/delivered gas in MCF: gas sold off-lease to a gatherer or purchaser. Within a month, sold can lag produced (tank and line-pack stock), so reconcile sold against produced cumulatively, not month by month; the gap between gross produced gas and this column is what you see comparing our gross series to marketed-gas series such as EIA's. NULL = the source did not report sold separately.\n", "enum": [] }, { "name": "gas_flared", "type": "int32", "nullable": true, "description": "Gas burned (flared) at the lease, in MCF. Kept separate from gas_vented because the split matters for emissions analysis (vented methane is far more potent than flared CO2). A source that reports only a combined figure populates gas_flared_vented instead, never a lossy split. NULL = not reported separately.\n", "enum": [] }, { "name": "gas_vented", "type": "int32", "nullable": true, "description": "Gas released unburned (vented) at the lease, in MCF. NULL = not reported separately.\n", "enum": [] }, { "name": "gas_flared_vented", "type": "int32", "nullable": true, "description": "Combined flared plus vented gas in MCF, for sources that report the two under a single code and cannot split them (e.g. the Texas RRC \"vented or flared\" code). A region that reports the split populates gas_flared and gas_vented and keeps this NULL; a region that reports only the combined figure populates this and keeps the split columns NULL, never a lossy split into one of them. NULL = no combined figure reported.\n", "enum": [] }, { "name": "gas_reinjected", "type": "int32", "nullable": true, "description": "Gas reinjected for pressure maintenance, cycling, gas lift, or enhanced recovery, in MCF. Large in Permian gas wells, and a major reason marketed gas runs far below gross. Can exceed the well's own produced gas (recycled gas-lift, purchased makeup gas, or allocation grain), so exclude it when balancing sold against produced.\n", "enum": [] }, { "name": "gas_lease_fuel", "type": "int32", "nullable": true, "description": "Gas consumed on-lease as fuel (engines, heaters, compressors), in MCF.\n", "enum": [] }, { "name": "gas_plant_fuel", "type": "int32", "nullable": true, "description": "Gas consumed as fuel at the processing plant, in MCF. Sparse, populated only where the source natively reports it.\n", "enum": [] }, { "name": "oil_sold", "type": "int32", "nullable": true, "description": "Marketed/sold oil plus condensate, in BBL. Only the sold split is carried for oil; other oil disposition (lease use, tank stock change) is noise at monthly grain. Oil includes condensate, matching the production series.\n", "enum": [] }, { "name": "gas_sold_origin", "type": "string", "nullable": true, "description": "How gas_sold was derived: reported = the source reported this value at well-month grain; lease_allocated = the source reported it at lease/unit level and we split it to wells using the same allocation weights as the monthly production series, so values roll up exactly to the lease total. A lease_allocated value is the well's share of its unit's volume and can exceed the well's own production where the unit handled more than this well, so compare sold vs produced at the unit level, not per single well. NULL exactly when gas_sold is NULL.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "gas_flared_origin", "type": "string", "nullable": true, "description": "How gas_flared was derived, same values as gas_sold_origin. NULL exactly when gas_flared is NULL. New Mexico reports flaring at well grain, the cleanest flaring data.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "gas_vented_origin", "type": "string", "nullable": true, "description": "How gas_vented was derived, same values as gas_sold_origin. NULL exactly when gas_vented is NULL.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "gas_flared_vented_origin", "type": "string", "nullable": true, "description": "How gas_flared_vented was derived, same values as gas_sold_origin. NULL exactly when gas_flared_vented is NULL. Texas reports the combined figure at lease grain; well values are allocated.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "gas_reinjected_origin", "type": "string", "nullable": true, "description": "How gas_reinjected was derived, same values as gas_sold_origin. NULL exactly when gas_reinjected is NULL.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "gas_lease_fuel_origin", "type": "string", "nullable": true, "description": "How gas_lease_fuel was derived, same values as gas_sold_origin. NULL exactly when gas_lease_fuel is NULL.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "gas_plant_fuel_origin", "type": "string", "nullable": true, "description": "How gas_plant_fuel was derived, same values as gas_sold_origin. NULL exactly when gas_plant_fuel is NULL.\n", "enum": [ "reported", "lease_allocated" ] }, { "name": "oil_sold_origin", "type": "string", "nullable": true, "description": "How oil_sold was derived, same values as gas_sold_origin. NULL exactly when oil_sold is NULL.\n", "enum": [ "reported", "lease_allocated" ] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "gom", "la", "nd", "nm", "tx", "wy" ], "regions_live_names": [ "Gulf of Mexico", "Louisiana", "North Dakota", "New Mexico", "Texas", "Wyoming" ] }, "gold_well_forecast_months": { "description": "Our deployed production forecast: one row per well per future month, oil and gas, starting the month after the well's last reported month and extending up to 120 months (truncated at the economic limit). oil_per_month and gas_per_month are expected values: additive across wells, so portfolio sums are portfolio forecasts. p10/p50/p90 bands appear where an uncertainty model backs them (petroleum convention: P10 optimistic). Which model produced a well's forecast lives in gold_well_forecast_provenance.", "tier": "portal", "primary_key": [ "well_id", "forecast_month" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "well_id", "type": "string", "nullable": false, "description": "Join key to the well register (gold_wells).\n", "enum": [] }, { "name": "forecast_month", "type": "date", "nullable": false, "description": "The month being forecast, always the first day of the month. Strictly after the well's last reported production month.\n", "enum": [] }, { "name": "year", "type": "int16", "nullable": false, "description": "Calendar year of the forecast month (equals the year of forecast_month). Provided for fast year-level filtering and partition pruning.\n", "enum": [] }, { "name": "oil_per_month", "type": "int32", "nullable": true, "description": "Mean (expected value) oil forecast in BBL/month. Always populated for oil-producing wells. Used directly for NPV calculations and additive for portfolio aggregation (the sum of well means is the portfolio mean). NULL for gas-only wells.\n", "enum": [] }, { "name": "oil_per_month_p10", "type": "int32", "nullable": true, "description": "Optimistic oil forecast in BBL/month (petroleum convention: a 10% chance of exceeding). NULL where no calibrated uncertainty model backs the well: the band is omitted rather than substituted with the point forecast, so a present band is always a real interval.\n", "enum": [] }, { "name": "oil_per_month_p50", "type": "int32", "nullable": true, "description": "Median oil forecast in BBL/month. Populated only where a quantile model with sufficient calibration depth backs it; NULL otherwise. Distinct from oil_per_month (the mean): production distributions are skewed, especially late in life, so median and mean legitimately diverge: both are honest values for different questions; don't substitute one for the other.\n", "enum": [] }, { "name": "oil_per_month_p90", "type": "int32", "nullable": true, "description": "Pessimistic oil forecast in BBL/month (petroleum convention: a 90% chance of exceeding). NULL where no uncertainty model backs the well.\n", "enum": [] }, { "name": "gas_per_month", "type": "int32", "nullable": true, "description": "Mean (expected value) gas forecast in MCF/month. NULL for oil-only wells. Same semantics as oil_per_month.\n", "enum": [] }, { "name": "gas_per_month_p10", "type": "int32", "nullable": true, "description": "Optimistic gas forecast in MCF/month (petroleum convention: a 10% chance of exceeding). NULL where no uncertainty model backs the well.\n", "enum": [] }, { "name": "gas_per_month_p50", "type": "int32", "nullable": true, "description": "Median gas forecast in MCF/month. Populated only where a quantile model backs it; for skewed distributions the median differs from the mean.\n", "enum": [] }, { "name": "gas_per_month_p90", "type": "int32", "nullable": true, "description": "Pessimistic gas forecast in MCF/month (petroleum convention: a 90% chance of exceeding). NULL where no uncertainty model backs the well.\n", "enum": [] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "ab", "ak", "al", "ar", "argentina", "bc", "brazil", "ca", "co", "gom", "ks", "la", "mb", "mexico", "mi", "ms", "mt", "nd", "nm", "oh", "ok", "pa", "pacific", "sk", "tx", "ut", "wv", "wy" ], "regions_live_names": [ "Alberta", "Alaska", "Alabama", "Arkansas", "Argentina", "British Columbia", "Brazil", "California", "Colorado", "Gulf of Mexico", "Kansas", "Louisiana", "Manitoba", "Mexico", "Michigan", "Mississippi", "Montana", "North Dakota", "New Mexico", "Ohio", "Oklahoma", "Pennsylvania", "Pacific OCS", "Saskatchewan", "Texas", "Utah", "West Virginia", "Wyoming" ] }, "gold_well_forecast_provenance": { "description": "The audit trail for every well's forecast: one row per well per product stream per forecast generation, recording the cohort the well belongs to, the winning forecast method, the training cutoff, and when it was generated. Join from the forecast months when you need to know which model produced a number.", "tier": "portal", "primary_key": [ "well_id", "stream" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "well_id", "type": "string", "nullable": false, "description": "Join key to the well register (gold_wells). Part of the primary key together with stream: one row per well per stream per generation.\n", "enum": [] }, { "name": "stream", "type": "string", "nullable": false, "description": "The production stream this row's forecast covers: oil or gas. Part of the primary key: a dual-product well has one provenance row per stream.\n", "enum": [ "oil", "gas" ] }, { "name": "atom_id_hash", "type": "string", "nullable": true, "description": "Identifier of the cohort the well was forecast under (opaque 12-character code). NULL for wells that fall outside any cohort (the data-quality fallback path).\n", "enum": [] }, { "name": "champion_method", "type": "string", "nullable": false, "description": "The method that produced this forecast: a decline-curve fit (e.g. arps_hyperbolic) or a machine-learning model (e.g. lgbm_ts_tweedie_monotone, catboost_ts_tweedie_monotone). A double-colon suffix qualifies the method with its variant or sub-path (e.g. lgbm_ts_tweedie_monotone::reanchored, type_curve_approx::in_cohort_terminal). Two reserved prefixes, ml_pending:: and ml_unsupported_serving::, would mark a serving fallback (the cohort's winning model is a machine-learning method but this well's delivered numbers fell back to a decline-curve fit; forecast_tier still reads champion). Neither appears in current data.\n", "enum": [] }, { "name": "forecast_tier", "type": "string", "nullable": false, "description": "How well-specific the model behind this forecast is, from most to least specific: champion = the backtested winning method for the well's own cohort; type_curve_approx = an approximate forecast from a cohort type curve, used where the well cannot carry its own model (lower confidence: treat as a badge, not a per-well fit); parent_cohort = a type curve from the cohort's parent pool; region_analog = a type curve at region x trajectory x stream level; per_well_dca = the well's own decline-curve fit; cross_region_analog = a type curve borrowed from an analog region (disabled pending a passing backtest: not present in current data); sub_region_formation = reserved for a future serving change (not emitted).\n", "enum": [ "champion", "parent_cohort", "region_analog", "sub_region_formation", "per_well_dca", "cross_region_analog", "type_curve_approx" ] }, { "name": "champion_cutoff", "type": "int16", "nullable": true, "description": "The training-history cutoff, in months, whose winning method produced this forecast. Chosen per well by age: short-history wells get a short-cutoff model, so wells in the same cohort can carry different cutoffs. NULL for the type-curve fallback tiers (parent_cohort / region_analog / cross_region_analog): no cutoff drove those forecasts.\n", "enum": [] }, { "name": "well_age_months_at_forecast", "type": "int16", "nullable": false, "description": "Number of producing months the well had when this forecast was generated. An audit signal: re-forecasting the well later may select a different model as it ages.\n", "enum": [] }, { "name": "recently_inactive", "type": "boolean", "nullable": true, "description": "Whether the well had effectively stopped producing this stream at forecast time: it produced in at most one of its most recent three reported months. For such wells the forecast is an expectation that assumes partial resumption, not a claim the well is actively producing; treat the near-term numbers as scenario-weighted. NULL when the well has fewer than three reported months of history.\n", "enum": [] }, { "name": "generated_at", "type": "timestamp_utc", "nullable": false, "description": "UTC timestamp when this forecast was computed: the forecast's \"as of\", and the way to detect a stale forecast.\n", "enum": [] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "ab", "ak", "al", "ar", "argentina", "bc", "brazil", "ca", "co", "gom", "ks", "la", "mb", "mexico", "mi", "ms", "mt", "nd", "nm", "oh", "ok", "pa", "pacific", "sk", "tx", "ut", "wv", "wy" ], "regions_live_names": [ "Alberta", "Alaska", "Alabama", "Arkansas", "Argentina", "British Columbia", "Brazil", "California", "Colorado", "Gulf of Mexico", "Kansas", "Louisiana", "Manitoba", "Mexico", "Michigan", "Mississippi", "Montana", "North Dakota", "New Mexico", "Ohio", "Oklahoma", "Pennsylvania", "Pacific OCS", "Saskatchewan", "Texas", "Utah", "West Virginia", "Wyoming" ] }, "gold_well_formation_surfaces": { "description": "Gridded formation-top surfaces: one row per (basin, formation, grid point) with the interpolated subsea top depth, its uncertainty, and formation thickness (isopach). Built from our formation-top picks; combine with directional surveys to determine where a wellbore landed.", "tier": "portal", "primary_key": [ "basin", "formation", "grid_lat", "grid_lon" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "basin", "type": "string", "nullable": false, "description": "Basin the grid is built for: the same basin vocabulary as the well register's basin column.\n", "enum": [] }, { "name": "formation", "type": "string", "nullable": false, "description": "Formation name for this surface, as the region's builder normalizes it (case conventions differ by region today). Name variants that resolve to one registry unit are pooled into a single surface under the most common name.\n", "enum": [] }, { "name": "formation_id", "type": "string", "nullable": true, "description": "Canonical stratigraphic-unit identifier: the join key to the formations register. NULL for surfaces built from names not in the registry (age-level names like \"Mississippian\", local names not yet curated).\n", "enum": [] }, { "name": "grid_lat", "type": "float64", "nullable": false, "description": "Grid point latitude (WGS84). Regular spacing per basin (0.01 degrees, about 1.1 km).\n", "enum": [] }, { "name": "grid_lon", "type": "float64", "nullable": false, "description": "Grid point longitude (WGS84). Regular spacing per basin.\n", "enum": [] }, { "name": "predicted_tvdss", "type": "int32", "nullable": false, "description": "Formation-top depth at this grid point, subsea, in feet. Negative = below sea level. Interpolated from our formation-top picks (the formation-tops register); no grid point is extrapolated beyond the data's extent.\n", "enum": [] }, { "name": "predicted_tvdss_stddev", "type": "int32", "nullable": false, "description": "Uncertainty of predicted_tvdss, in feet (one standard error), calibrated on held-out wells so that plus or minus 2 standard errors has honest coverage. Use it to mask or down-weight low-confidence areas.\n", "enum": [] }, { "name": "isopach_ft", "type": "int32", "nullable": true, "description": "Formation thickness at this grid point, in feet: the distance down to the next formation surface below. NULL for the deepest surface at the point. Computed by actual local depth ordering, so values are never negative.\n", "enum": [] }, { "name": "n_nearby", "type": "int16", "nullable": true, "description": "Number of formation-top observations within 5 miles of this grid point: a data-density indicator, complementary to predicted_tvdss_stddev (how close the control points are vs how confident the model is). Capped at 10,000.\n", "enum": [] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "ab", "mt", "nd", "oh", "tx", "ut", "wv", "wy" ], "regions_live_names": [ "Alberta", "Montana", "North Dakota", "Ohio", "Texas", "Utah", "West Virginia", "Wyoming" ] }, "gold_well_formation_tops": { "description": "Formation top picks: one row per well per geologic formation penetrated, with the measured top depth (TVD and subsea). Sourced from completion reports, well logs and scout tickets; this is the input data behind our gridded formation surfaces.", "tier": "portal", "primary_key": [ "well_id", "formation" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "well_id", "type": "string", "nullable": false, "description": "Join key to the well register. Part of the primary key together with formation.\n", "enum": [] }, { "name": "formation", "type": "string", "nullable": false, "description": "Formation name for this pick, as the region's builder normalizes it. Case conventions differ by region today (several regions publish uppercase names), so the same formation can appear under more than one spelling across regions; filters on this column match exactly. Part of the primary key.\n", "enum": [] }, { "name": "zone", "type": "string", "nullable": true, "description": "Landing zone within the formation: an attribute, not part of the key. Where multiple records exist for a (well, formation) pair, carries the shallowest record's zone. NULL = formation-level top with no zone detail.\n", "enum": [] }, { "name": "formation_id", "type": "string", "nullable": true, "description": "Canonical stratigraphic-unit identifier: the join key to the formations register. NULL for formation names not yet mapped to the registry.\n", "enum": [] }, { "name": "top_tvd", "type": "int32", "nullable": true, "description": "True vertical depth to the formation top, in feet: the shallowest value when multiple sources report. Sourced from completion-report formation lists. NULL when the source reports only a measured depth we have not converted: no as-drilled survey coverage exists at that depth (top_md still carries the reported depth).\n", "enum": [] }, { "name": "top_md", "type": "int32", "nullable": true, "description": "Measured depth to the formation top, in feet. NULL when the source reports only TVD (the common case in Texas).\n", "enum": [] }, { "name": "top_tvdss", "type": "int32", "nullable": true, "description": "Subsea depth of the top, in feet: elevation_kb minus top_tvd. Negative = below sea level. NULL when elevation_kb or top_tvd is unavailable. The elevation-normalized depth our formation surfaces are built from.\n", "enum": [] }, { "name": "top_tvd_source", "type": "string", "nullable": true, "description": "Where top_tvd came from: reported = the operator-reported value, either confirmed by the well's directional survey within 50 ft or with no survey to check against; survey = the operator value disagreed with the survey by more than 50 ft and was replaced by the survey-interpolated depth at top_md. survey_filled = the source reported only a measured depth; the value is the survey-interpolated true vertical depth at that measured depth. NULL, together with top_tvd, where the source reported only a measured depth and no conversion exists: we know the measured depth (top_md) and genuinely do not know the true vertical depth.\n", "enum": [ "reported", "survey", "survey_filled" ] }, { "name": "pick_source", "type": "string", "nullable": true, "description": "Who authored this formation pick: operator_report = the operator's own filed formation list (completion reports and well files); regulator_log_pick = the regulator's or geological survey's own interpretation of well logs. Empty where the pick's authorship is not yet classified.\n", "enum": [ "operator_report", "regulator_log_pick" ] }, { "name": "base_tvd", "type": "int32", "nullable": true, "description": "Depth of the formation's base (bottom boundary) at this well, true vertical depth in feet, from operator picks explicitly marked as the base (e.g. 'BASE AUSTIN CHALK'). NULL when no base pick was reported; most wells report only the top.\n", "enum": [] }, { "name": "base_md", "type": "int32", "nullable": true, "description": "Measured depth along the wellbore of the formation's base pick, in feet. NULL when no base pick was reported.\n", "enum": [] }, { "name": "base_tvdss", "type": "int32", "nullable": true, "description": "The formation's base in true vertical depth subsea, feet, same datum convention as top_tvdss. NULL when no base pick was reported.\n", "enum": [] }, { "name": "elevation_kb", "type": "int32", "nullable": true, "description": "Surface elevation (kelly bushing datum), in feet, copied from the well register so subsea depth can be recomputed. NULL = elevation unknown.\n", "enum": [] }, { "name": "latitude", "type": "float64", "nullable": true, "description": "Surface hole latitude (WGS84), copied from the well register for spatial queries.\n", "enum": [] }, { "name": "longitude", "type": "float64", "nullable": true, "description": "Surface hole longitude (WGS84), copied from the well register.\n", "enum": [] } ], "regional_columns": [], "region_extras": { "wy": [ { "name": "source", "type": "string", "description": "" }, { "name": "top_md_method", "type": "string", "description": "" } ] }, "serving_derived": [], "data_currency": [], "regions_live": [ "ab", "mi", "mt", "nd", "oh", "tx", "ut", "wv", "wy" ], "regions_live_names": [ "Alberta", "Michigan", "Montana", "North Dakota", "Ohio", "Texas", "Utah", "West Virginia", "Wyoming" ] }, "gold_well_fracs": { "description": "One row per hydraulic-fracturing job, reconciled across FracFocus and state filings so one physical treatment appears exactly once. Carries treatment dates, total proppant and water volumes, fluid-system classification, and stage count. Where FracFocus and the state disagree, we keep the better value and say which source supplied it: each key measurement carries its own paired _source column (proppant_lbs_source, total_water_gal_source, frac_stages_source).", "tier": "portal", "primary_key": [ "frac_id" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "frac_id", "type": "string", "nullable": false, "description": "Globally unique frac-treatment identifier (opaque string) - this table's primary key. One physical treatment appears exactly once, reconciled across FracFocus and state filings. Never parse substrings out of it.\n", "enum": [] }, { "name": "well_id", "type": "string", "nullable": false, "description": "Join key to the well register.\n", "enum": [] }, { "name": "completion_id", "type": "string", "nullable": true, "description": "Join key to the completion register - the completion event this treatment belongs to. NULL when no completion could be matched.\n", "enum": [] }, { "name": "frac_start_date", "type": "date", "nullable": false, "description": "Start of the treatment.\n", "enum": [] }, { "name": "frac_end_date", "type": "date", "nullable": true, "description": "End of the treatment. NULL when the source reports only a start date. Always on or after frac_start_date.\n", "enum": [] }, { "name": "total_water_gal", "type": "float64", "nullable": true, "description": "Total base water volume in gallons, primarily from FracFocus.\n", "enum": [] }, { "name": "proppant_lbs", "type": "float64", "nullable": true, "description": "Total proppant mass in pounds, aggregated from the chemical registry.\n", "enum": [] }, { "name": "proppant_type", "type": "string", "nullable": true, "description": "Proppant classification: sand, ceramic, resin_coated, or mixed. Derived from the chemical registry.\n", "enum": [ "sand", "ceramic", "resin_coated", "mixed" ] }, { "name": "frac_type", "type": "string", "nullable": true, "description": "Treatment fluid classification: slickwater, hybrid, gel, or acid. Derived from the FracFocus chemical registry.\n", "enum": [ "slickwater", "hybrid", "gel", "acid" ] }, { "name": "frac_stages", "type": "int16", "nullable": true, "description": "Number of frac stages. Often from state filings - FracFocus rarely reports it.\n", "enum": [] }, { "name": "operator", "type": "string", "nullable": true, "description": "The operator responsible for this treatment, as a canonical company name. Where the frac filing names an operator, this is the operator at the time of the treatment - a point-in-time fact. Where the filing names none, the well register's operator stands in where we can resolve one, which for an older treatment can name a company other than the one that performed the job.\n", "enum": [] }, { "name": "operator_entity", "type": "string", "nullable": true, "description": "Raw entity name from the frac filing, preserved without normalization. NULL where the filing names no operator; in Texas and New Mexico the operator column then carries the well register's operator where one resolves.\n", "enum": [] }, { "name": "proppant_lbs_source", "type": "string", "nullable": true, "description": "Which source reported proppant_lbs: fracfocus, completion_report, or sundry_notice. State filings win over FracFocus when both report. NULL exactly when proppant_lbs is NULL.\n", "enum": [ "fracfocus", "completion_report", "sundry_notice" ] }, { "name": "total_water_gal_source", "type": "string", "nullable": true, "description": "Which source reported total_water_gal: fracfocus, completion_report, or sundry_notice. State filings win over FracFocus when both report. NULL exactly when total_water_gal is NULL.\n", "enum": [ "fracfocus", "completion_report", "sundry_notice" ] }, { "name": "frac_stages_source", "type": "string", "nullable": true, "description": "Which source reported frac_stages: fracfocus, completion_report, or sundry_notice. FracFocus rarely reports stages; state filings usually do. NULL exactly when frac_stages is NULL.\n", "enum": [ "fracfocus", "completion_report", "sundry_notice" ] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "ab", "ak", "al", "ar", "argentina", "bc", "ca", "co", "ks", "la", "ms", "mt", "nd", "nm", "oh", "ok", "pa", "tx", "ut", "wv", "wy" ], "regions_live_names": [ "Alberta", "Alaska", "Alabama", "Arkansas", "Argentina", "British Columbia", "California", "Colorado", "Kansas", "Louisiana", "Mississippi", "Montana", "North Dakota", "New Mexico", "Ohio", "Oklahoma", "Pennsylvania", "Texas", "Utah", "West Virginia", "Wyoming" ] }, "gold_well_injection": { "description": "Monthly volumes injected INTO disposal, enhanced-recovery and storage wells: water (BBL) and gas (MCF), one row per injection well per month, with the injection type. This is fluid going down the hole; produced water lives on the production table. NULL means not reported, never zero.", "tier": "portal", "primary_key": [ "well_id", "date" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "well_id", "type": "string", "nullable": false, "description": "Join key to the well register: the injection or disposal well that received the fluid. Always populated. Most injection wells are not producers (many are converted to disposal), so this population is largely separate from the monthly production series.\n", "enum": [] }, { "name": "date", "type": "date", "nullable": false, "description": "Injection month, always the first day of the month.\n", "enum": [] }, { "name": "year", "type": "int16", "nullable": false, "description": "Calendar year of the injection month (equals the year of date). Provided for fast year-level filtering and partition pruning.\n", "enum": [] }, { "name": "water_injected", "type": "int32", "nullable": true, "description": "Liquid injected during the month, in barrels (BBL): saltwater for disposal wells, water for waterfloods. The dominant injection signal. NULL means no liquid volume was reported that month (never zero); 0 is a reported zero. Where a source reports per-zone volumes (e.g. Alaska, California), zones are summed to the well-month.\n", "enum": [] }, { "name": "gas_injected", "type": "int32", "nullable": true, "description": "Gas injected during the month, in thousand cubic feet (MCF): enhanced recovery, pressure maintenance, or cycling. NULL where not reported, never zero. CO2 injected for enhanced recovery and reported in MCF is included here.\n", "enum": [] }, { "name": "injection_type", "type": "string", "nullable": true, "description": "The well's injection class for this volume: disposal (saltwater disposal), enhanced_recovery (waterflood / enhanced oil recovery), storage (hydrocarbon or gas storage), or other. Mapped from the regulator's well-class code. Carried per row because a well can change injection purpose over its life. NULL where unknown.\n", "enum": [ "disposal", "enhanced_recovery", "storage", "other" ] }, { "name": "record_origin", "type": "string", "nullable": false, "description": "How the volume was derived: reported = the source reports it directly per well; lease_allocated = a field or unit total split to wells using the same allocation weights as the monthly production series; wellstar_estimated = California's own preliminary-estimate flag on the source record, still a source-reported volume, marked provisional by the source, never one we modeled; identity_inferred = the volume is the source's own well-month figure, but the source omitted which well it belongs to; the well shown is our attribution, recovered by matching the row's stable attributes (for example the operator and the well's packer depth) against the same source's named filings in adjacent years, and published only where that match is unambiguous and its measured accuracy clears a 95% floor. Always populated.\n", "enum": [ "reported", "lease_allocated", "wellstar_estimated", "identity_inferred" ] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [ { "region": "la", "region_name": "Louisiana", "as_of": "2025-12-01", "customer_note": null } ], "regions_live": [ "ab", "ak", "ar", "bc", "ca", "la", "nm", "ok", "tx", "wy" ], "regions_live_names": [ "Alberta", "Alaska", "Arkansas", "British Columbia", "California", "Louisiana", "New Mexico", "Oklahoma", "Texas", "Wyoming" ] }, "gold_well_permits": { "description": "One row per drilling permit, covering every permit on file (pending, approved, rejected, expired, cancelled, and drilled), so the table reads as the forward-looking activity pipeline. Amendments update the permit's row (last_amended_date marks them) rather than creating duplicates. Carries the permitted well's identity and proposed location (including bottom-hole for horizontals), the operator at filing and today, and proposed depth, formation, and purpose. well_id is NULL until a well exists.", "tier": "portal", "primary_key": [ "permit_id" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "permit_id", "type": "string", "nullable": false, "description": "Globally unique permit identifier (opaque string), this table's primary key. Stable across time; never parse substrings out of it.\n", "enum": [] }, { "name": "well_id", "type": "string", "nullable": true, "description": "Join key to the well register. NULL while no well exists (pending or rejected filings); set once the well is created at permit approval.\n", "enum": [] }, { "name": "permit_number", "type": "string", "nullable": true, "description": "Agency-assigned permit identifier. TX: RRC district-sequence (08-123456). ND: NDIC permit number. Format varies by state. NULL where the source assigns no permit number (New Mexico, West Virginia).\n", "enum": [] }, { "name": "country", "type": "string", "nullable": false, "description": "Country code (ISO 3166-1 alpha-2, upper-case, e.g. US, CA).\n", "enum": [] }, { "name": "state_province", "type": "string", "nullable": false, "description": "Full name of the state or province the well sits in (e.g. 'Texas', 'Alberta').\n", "enum": [] }, { "name": "state_province_code", "type": "string", "nullable": false, "description": "Jurisdiction code within the country (e.g. TX, AB); paired with country it forms a globally unique jurisdiction key.\n", "enum": [] }, { "name": "well_name", "type": "string", "nullable": true, "description": "Proposed well name from the permit application. May differ from the final name in the well register.\n", "enum": [] }, { "name": "permit_type", "type": "string", "nullable": true, "description": "What the permit authorizes: new_drill, recompletion, deepening, re_entry, sidetrack, plug, reclass, or other. Mapped from each state's own codes.\n", "enum": [ "new_drill", "recompletion", "deepening", "re_entry", "sidetrack", "plug", "reclass", "other" ] }, { "name": "status", "type": "string", "nullable": true, "description": "Current permit status: pending, approved, expired, rejected, cancelled, or drilled. The full lifecycle including terminal states; drilled is derived automatically once the linked well has a spud date.\n", "enum": [ "pending", "approved", "expired", "rejected", "cancelled", "drilled" ] }, { "name": "filed_date", "type": "date", "nullable": true, "description": "Date the permit application was submitted to the regulatory agency. For an amended application this is the date the latest amendment was received.\n", "enum": [] }, { "name": "approved_date", "type": "date", "nullable": true, "description": "Date the agency approved the permit. NULL when the permit is pending, was rejected, or was cancelled before approval. Also NULL when our source feed does not carry the approval date: the feed may start after the permit was issued, or record only related processing steps.\n", "enum": [] }, { "name": "expiration_date", "type": "date", "nullable": true, "description": "Scheduled permit validity end date, set at approval. The date the permit will (or did) expire if not drilled. Present on approved, expired, and drilled permits.\n", "enum": [] }, { "name": "cancelled_date", "type": "date", "nullable": true, "description": "Date the operator withdrew or the agency cancelled the permit. Some agencies record one without moving the permit status to cancelled; both are published as reported.\n", "enum": [] }, { "name": "reported_date", "type": "date", "nullable": true, "description": "Date the source agency first published this permit, useful for monitoring new activity. NULL for permits loaded from historical archives.\n", "enum": [] }, { "name": "last_amended_date", "type": "date", "nullable": true, "description": "Effective date of the most recent amendment. NULL = original filing, never amended. When populated, the permit's characteristics (tvd, md, formation, and so on) reflect the amended version; only the latest state is carried.\n", "enum": [] }, { "name": "record_origin", "type": "string", "nullable": false, "description": "How this permit row came to exist: reported = a source-published permit filing (regulator daily report or permit database); inferred = reconstructed from the well register for a well with no separate permit filing in our records (e.g. ND wells permitted before 2005). Inferred rows carry NULL filed/approved dates by construction, and this flag discloses why. Always populated. Filter record_origin = 'reported' for actual filings only.\n", "enum": [ "reported", "inferred" ] }, { "name": "operator", "type": "string", "nullable": true, "description": "The company that holds this permit today, as a canonical company name with mergers and acquisitions applied as of today, so Occidental's permit book includes inherited Anadarko filings. Sourced from the filing where the permit names its operator; where the source publishes no operator on the permit itself, we carry the well's operator of record instead. NULL when neither names one.\n", "enum": [] }, { "name": "operator_id", "type": "string", "nullable": true, "description": "Stable company identifier for operator, the holder as of today. Join key to the organizations register. NULL when unresolved. Populated even where reported_operator_id is NULL: for permits whose filing names no operator, the holder comes from the well record rather than from correcting the filing.\n", "enum": [] }, { "name": "reported_operator", "type": "string", "nullable": true, "description": "The operator as the source's permit filing records it, normalized to a canonical display name but with NO merger succession applied: the faithful filing record. Where both are present, differs from operator exactly where our ownership graph corrected a stale operator-of-record. NULL where the permit filing itself names no operator (some regulators publish permits without one); operator then carries the well's operator of record instead.\n", "enum": [] }, { "name": "reported_operator_id", "type": "string", "nullable": true, "description": "Stable company identifier for reported_operator (no merger succession). NULL when the raw filing name is not yet mapped to a registered organization.\n", "enum": [] }, { "name": "reported_operator_entity", "type": "string", "nullable": true, "description": "Raw filing entity name from the permit application: the legal entity as the permit filing itself names it, before any normalization. NULL where the filing names no real company (the regulator publishes permits without an operator field, or uses placeholder strings like \"historic owner\" or \"not assigned\", which we treat as no operator rather than publish as one), and where we cannot read the name from the filing itself; the name is never substituted from another register. Useful for audit and M&A analysis.\n", "enum": [] }, { "name": "reported_operator_registration_id", "type": "string", "nullable": true, "description": "The regulator-issued ID of the filing operator (TX P-5 number and each region's equivalent). Where the filing carries one, it is passed through raw as an opaque string. Where the regulator issues licence IDs but never prints them on permit filings (currently Kansas), it is our match of the filing operator's name to the state's licensee register, derived by us rather than filed. NULL otherwise.\n", "enum": [] }, { "name": "trajectory", "type": "string", "nullable": true, "description": "Planned well trajectory: horizontal, vertical, or directional. Same values as the well register. Mapped from state-specific flags or codes.\n", "enum": [ "horizontal", "vertical", "directional" ] }, { "name": "primary_product", "type": "string", "nullable": true, "description": "Oil or gas, the product the permit is for. Where the application states one product, that is the value. Where the application states both, states nothing, or lists fields that disagree, we resolve it with our calibrated estimate from the details the filing carries (the fields or formation it names where it lists them, its location, depth and era) and the wells drilled around it: the product of the play it targets, published only where it clears the region's measured agreement bar against what such permits' wells went on to produce. See primary_product_source for which. NULL where no signal clears the bar, and for permits whose purpose is not production (injection, disposal, storage, observation, service, stratigraphic test; see well_purpose) unless the filing states a product.\n", "enum": [ "oil", "gas" ] }, { "name": "primary_product_source", "type": "string", "nullable": true, "description": "Which signal set primary_product on this permit: filing = the application states this product; inferred = the application stated both products, none, or fields that disagree, and this is our calibrated estimate from the details the filing carries, its location, depth, era and neighbouring wells, made only where it clears the region's measured agreement bar against what such permits' wells went on to produce (published on the methodology page). NULL exactly when primary_product is NULL.\n", "enum": [ "filing", "inferred" ] }, { "name": "well_purpose", "type": "string", "nullable": true, "description": "Intended well purpose: producer, injector, disposal, storage, observation, service, stratigraphic_test, or other. Same values as the well register. From the permit application.\n", "enum": [ "producer", "injector", "disposal", "storage", "observation", "service", "stratigraphic_test", "other" ] }, { "name": "is_offshore", "type": "boolean", "nullable": true, "description": "Whether the permitted location is offshore, as the source classifies it. Stable: a well doesn't move onshore.\n", "enum": [] }, { "name": "tvd", "type": "int32", "nullable": true, "description": "Proposed true vertical depth (feet). From the permit application. In Texas and Wyoming the regulator files a single unqualified well depth; it behaves as a vertical depth and is published here, though a minority of filings carry the measured depth instead.\n", "enum": [] }, { "name": "md", "type": "int32", "nullable": true, "description": "Proposed total measured depth (feet). From the permit application.\n", "enum": [] }, { "name": "formation", "type": "string", "nullable": true, "description": "Target formation as reported by the operator on the permit application. Not normalized (operator-reported); may differ from the well register's formation. In Oklahoma an application can list up to ten target formations; the deepest declared target is published. In Ohio the column is filled only where the application names a single target formation we can match; it is NULL where the application lists several targets or a range, joins names with a hyphen (which we do not split), or gives a name we cannot match.\n", "enum": [] }, { "name": "zone", "type": "string", "nullable": true, "description": "Target landing zone where specified on the permit. Same formation/zone convention as the well register. NULL where not available.\n", "enum": [] }, { "name": "latitude", "type": "float64", "nullable": true, "description": "Proposed surface hole location latitude (WGS84).\n", "enum": [] }, { "name": "longitude", "type": "float64", "nullable": true, "description": "Proposed surface hole location longitude (WGS84).\n", "enum": [] }, { "name": "bhl_latitude", "type": "float64", "nullable": true, "description": "Proposed bottom-hole latitude from the permit filing (WGS84). Vertical filings that state a bottom hole, typically coinciding with the surface location, are published as filed. NULL where the filing states no bottom hole we can source to it: many vertical wells state none, some regulators publish only a footage call, and some publish a coordinate we cannot distinguish from the as-drilled record.\n", "enum": [] }, { "name": "bhl_longitude", "type": "float64", "nullable": true, "description": "Proposed bottom-hole longitude from the permit filing (WGS84). Vertical filings that state a bottom hole, typically coinciding with the surface location, are published as filed. NULL where the filing states no bottom hole we can source to it: many vertical wells state none, some regulators publish only a footage call, and some publish a coordinate we cannot distinguish from the as-drilled record.\n", "enum": [] }, { "name": "basin", "type": "string", "nullable": true, "description": "Basin assignment from spatial lookup on the proposed surface location.\n", "enum": [] }, { "name": "sub_basin", "type": "string", "nullable": true, "description": "Structural sub-unit of the basin from spatial lookup, populated only where a real named sub-unit exists, never a play name. NULL otherwise.\n", "enum": [] }, { "name": "field", "type": "string", "nullable": true, "description": "Field the permit names, as filed with the regulator and in the regulator's own naming. NULL where the filing names no field: a wildcat, unknown or undefined designation is published as NULL, not as a field; and NULL where a filing names several fields without the source's completion record singling one out; applied as each region's permits rebuild under this contract, so a region not yet rebuilt may still show such a designation.\n", "enum": [] } ], "regional_columns": [], "region_extras": { "ab": [ { "name": "licence_number", "type": "string", "description": "" } ], "bc": [ { "name": "wa_number", "type": "string", "description": "" } ], "ca": [ { "name": "county", "type": "string", "description": "" }, { "name": "county_unique", "type": "string", "description": "" }, { "name": "county_fips", "type": "string", "description": "" } ], "co": [ { "name": "perm_type", "type": "string", "description": "" }, { "name": "prop_depth_ft", "type": "int32", "description": "" } ], "ks": [ { "name": "county", "type": "string", "description": "" }, { "name": "county_unique", "type": "string", "description": "" }, { "name": "county_fips", "type": "string", "description": "" }, { "name": "township", "type": "string", "description": "" }, { "name": "range", "type": "string", "description": "" }, { "name": "section", "type": "string", "description": "" }, { "name": "lease_name", "type": "string", "description": "" } ], "la": [ { "name": "la_permit_id", "type": "string", "description": "" }, { "name": "la_well_serial", "type": "string", "description": "" }, { "name": "district", "type": "string", "description": "" }, { "name": "county", "type": "string", "description": "" }, { "name": "county_unique", "type": "string", "description": "" }, { "name": "county_fips", "type": "string", "description": "" } ], "mt": [ { "name": "county", "type": "string", "description": "" }, { "name": "county_unique", "type": "string", "description": "" }, { "name": "county_fips", "type": "string", "description": "" }, { "name": "mbogc_dor_id", "type": "string", "description": "" }, { "name": "mbogc_slant", "type": "string", "description": "" } ], "nd": [ { "name": "file_no", "type": "int64", "description": "" } ], "nm": [ { "name": "ocd_district", "type": "string", "description": "" }, { "name": "lease_type", "type": "string", "description": "" } ], "pa": [ { "name": "county", "type": "string", "description": "" }, { "name": "county_unique", "type": "string", "description": "" }, { "name": "county_fips", "type": "string", "description": "" }, { "name": "municipality", "type": "string", "description": "" }, { "name": "lease_name", "type": "string", "description": "" }, { "name": "unconventional", "type": "boolean", "description": "" }, { "name": "dep_region", "type": "string", "description": "" }, { "name": "authorization_id", "type": "int64", "description": "" } ], "tx": [ { "name": "tx_permit_id", "type": "string", "description": "" }, { "name": "tx_well_id", "type": "string", "description": "" }, { "name": "district", "type": "string", "description": "" }, { "name": "county", "type": "string", "description": "" }, { "name": "county_unique", "type": "string", "description": "" }, { "name": "county_fips", "type": "string", "description": "" }, { "name": "lease_name", "type": "string", "description": "" } ], "wv": [ { "name": "county", "type": "string", "description": "" }, { "name": "county_unique", "type": "string", "description": "" }, { "name": "county_fips", "type": "string", "description": "" }, { "name": "api14", "type": "string", "description": "" }, { "name": "permit_action", "type": "string", "description": "" }, { "name": "well_type_wv", "type": "string", "description": "" } ], "wy": [ { "name": "county", "type": "string", "description": "" }, { "name": "county_unique", "type": "string", "description": "" }, { "name": "county_fips", "type": "string", "description": "" }, { "name": "apd_number", "type": "string", "description": "" }, { "name": "well_class_wy", "type": "string", "description": "" } ] }, "serving_derived": [], "data_currency": [], "regions_live": [ "ab", "ak", "ar", "bc", "ca", "co", "ks", "la", "mt", "nd", "nm", "oh", "ok", "pa", "tx", "ut", "wv", "wy" ], "regions_live_names": [ "Alberta", "Alaska", "Arkansas", "British Columbia", "California", "Colorado", "Kansas", "Louisiana", "Montana", "North Dakota", "New Mexico", "Ohio", "Oklahoma", "Pennsylvania", "Texas", "Utah", "West Virginia", "Wyoming" ] }, "gold_well_production": { "description": "Monthly production volumes for every well, one row per well per month. The series is complete and continuous from first production to the well's reporting frontier: alongside volumes exactly as reported, it includes reliably-inferred rows (interior gap fills, lease-to-well allocations, period-to-month splits), each labeled in record_origin so you can always filter to the raw reported subset. Volumes are monthly totals; per-day rates, cumulatives, and month counts are intentionally not stored. They derive from this table in one SQL expression (see the derived-fields section). Operator columns give both the owner at that month (M&A applied) and the operator exactly as the source reported it.", "tier": "portal", "primary_key": [ "well_id", "date" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "well_id", "type": "string", "nullable": false, "description": "Globally unique well identifier (opaque string), the join key to the well register (gold_wells) and every other well-grain table. Stable across time; never parse substrings out of it.\n", "enum": [] }, { "name": "date", "type": "date", "nullable": false, "description": "Production month, always the first day of the month (a 2026-03 row is dated 2026-03-01). Together with well_id this is the primary key.\n", "enum": [] }, { "name": "year", "type": "int16", "nullable": false, "description": "Calendar year of the production month (equals the year of date). Provided for fast year-level filtering and partition pruning.\n", "enum": [] }, { "name": "oil_per_month", "type": "int32", "nullable": false, "description": "Oil produced during the month, in barrels (BBL). Includes condensate. Never NULL: a reported zero, a reliably-inferred zero, and a placeholder zero all appear as 0, with record_origin telling you which (see source_corrupt for placeholder zeros where the source's stored figures were discarded as corrupt). NGLs are excluded.\n", "enum": [] }, { "name": "gas_per_month", "type": "int32", "nullable": false, "description": "Natural gas produced during the month, in thousand cubic feet (MCF). Hydrocarbon gas only: non-hydrocarbon volumes a source books in its gas column (carbon dioxide, helium, nitrogen) are excluded. Gross wellhead gas; see the disposition table for how gas was used or sold. Never NULL.\n", "enum": [] }, { "name": "water_per_month", "type": "int32", "nullable": true, "description": "Water produced during the month, in barrels (BBL). NULL where the source does not report well-level water (e.g. TX, OK): NULL means \"not reported\", never zero.\n", "enum": [] }, { "name": "producing_days", "type": "int16", "nullable": true, "description": "Number of days the well actually produced during the month, as reported. NULL where the source does not report it, and where a reported count was refused as outside the 0-31 range a month can hold; in Pennsylvania and Ohio a spread filing's zero-day months that still carry volume are NULL as well. Note: per-day rates in our serving layers divide by calendar days, not producing days, so rates stay comparable across sources.\n", "enum": [] }, { "name": "operator", "type": "string", "nullable": true, "description": "The company operating the well during THIS month, as a canonical company name (e.g. \"EOG Resources\"): mergers and acquisitions are applied as of the production month, so a well acquired in 2022 shows the buyer from 2022 onward and the previous owner before that. NULL only when the source provides no operator at all. A change in operator between a month the source dated and a month it did not marks where our dated evidence ends, not a dated ownership event.\n", "enum": [] }, { "name": "operator_id", "type": "string", "nullable": true, "description": "Stable company identifier for operator: the owner at this month. Join key to the organizations register. NULL when the operator name cannot be resolved to a registered organization.\n", "enum": [] }, { "name": "reported_operator", "type": "string", "nullable": true, "description": "The operator exactly as the regulatory source records it for this month, normalized to a canonical display name but with NO merger succession applied: the faithful regulatory record. Where this differs from operator, our ownership graph corrected a stale operator-of-record at the source. NULL wherever the source gives us no operator we can present as a company for that month: it may publish nothing at all, only a placeholder for an unknown or orphaned operator (a state plugging fund, an \"unknown operator\" literal), or only a contract or licence identifier we have not yet mapped to its operator.\n", "enum": [] }, { "name": "reported_operator_id", "type": "string", "nullable": true, "description": "Stable company identifier for reported_operator (no merger succession). operator_id differing from reported_operator_id means we corrected the source's stale record. NULL wherever reported_operator is NULL (see there), and additionally where a usable published name is not yet mapped to a registered organization, so a NULL id beside a populated reported_operator_entity means an unmapped name, not a missing operator.\n", "enum": [] }, { "name": "reported_operator_entity", "type": "string", "nullable": true, "description": "Raw reporting entity name from the source (e.g. \"EOG New Mexico\"), before any normalization or company resolution. No merger succession is applied: this is the source's own string, not our corrected view of who owns the well today. NULL where the source names no real company: regulator placeholder strings (\"historic owner\", \"not assigned\") are treated as no operator rather than published as one. Also empty on months we filled in ourselves (record_origin = gap_filled): the source reported nothing for that month; a region's filled-in months read this way from its next production refresh. Useful for audit and M&A analysis.\n", "enum": [] }, { "name": "reported_operator_registration_id", "type": "string", "nullable": true, "description": "The regulator-issued operator ID at the time of production (TX P-5 number, ND operator number, etc.). Where the source filing carries one, it is passed through raw as an opaque string. Where the regulator issues licence IDs but never prints them on production records (currently Kansas), it is our match of the reported operator name to the state's own licensee register: the same ID namespace, derived by us rather than filed. NULL otherwise.\n", "enum": [] }, { "name": "record_origin", "type": "string", "nullable": false, "description": "How this row was derived: the provenance flag. Values: reported (as filed with the source), gap_filled (a reliably-inferred zero inside a well's reporting history), lease_allocated (lease-level volume allocated to wells), period_allocated (multi-month filing split to months), reconciled (adjusted to match an official published total), wellstar_estimated (California's own preliminary-estimate flag), source_corrupt (placeholder zeros for filed figures we discarded as corrupt). Filter record_origin = 'reported' for the raw source view, noting that inside a declared discard window (see source_corrupt) the discarded stream's figures are placeholder zeros on every origin, reported rows included.\n", "enum": [ "reported", "gap_filled", "lease_allocated", "period_allocated", "reconciled", "wellstar_estimated", "source_corrupt" ] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [ { "name": "oil_per_day", "formula": "oil_per_month / date_part('day', last_day(date))", "description": "Average oil rate for the month in BBL/d, using calendar days (not producing days) so rates are comparable across sources and wells." }, { "name": "gas_per_day", "formula": "gas_per_month / date_part('day', last_day(date))", "description": "Average gas rate for the month in MCF/d, calendar-day basis." }, { "name": "water_per_day", "formula": "water_per_month / date_part('day', last_day(date))", "description": "Average water rate for the month in BBL/d, calendar-day basis. NULL where water_per_month is NULL." }, { "name": "oil_cum", "formula": "SUM(oil_per_month) OVER (PARTITION BY well_id ORDER BY date)", "description": "Cumulative oil (BBL) from first production through this month." }, { "name": "gas_cum", "formula": "SUM(gas_per_month) OVER (PARTITION BY well_id ORDER BY date)", "description": "Cumulative gas (MCF) from first production through this month." }, { "name": "water_cum", "formula": "SUM(water_per_month) OVER (PARTITION BY well_id ORDER BY date)", "description": "Cumulative water (BBL) from first production through this month." }, { "name": "months_on_production", "formula": "CASE WHEN date >= MIN(CASE WHEN oil_per_month > 0 OR gas_per_month > 0 THEN date END) OVER (PARTITION BY well_id) THEN 1 + datediff('month', MIN(CASE WHEN oil_per_month > 0 OR gas_per_month > 0 THEN date END) OVER (PARTITION BY well_id), date) END", "description": "Calendar months elapsed since the well's first month with any oil or gas (that month = 1), counting idle months. NULL before first production. The x-axis for type-curve and decline analysis." }, { "name": "producing_months", "formula": "SUM(CASE WHEN oil_per_month > 0 OR gas_per_month > 0 THEN 1 ELSE 0 END) OVER (PARTITION BY well_id ORDER BY date)", "description": "Running count of months with actual production (oil or gas above zero): unlike months_on_production, idle months don't advance it." } ], "data_currency": [], "regions_live": [ "ab", "ak", "al", "ar", "argentina", "bc", "brazil", "ca", "co", "gom", "ks", "la", "mb", "mexico", "mi", "ms", "mt", "nd", "nm", "oh", "ok", "pa", "pacific", "sk", "tx", "ut", "wv", "wy" ], "regions_live_names": [ "Alberta", "Alaska", "Alabama", "Arkansas", "Argentina", "British Columbia", "Brazil", "California", "Colorado", "Gulf of Mexico", "Kansas", "Louisiana", "Manitoba", "Mexico", "Michigan", "Mississippi", "Montana", "North Dakota", "New Mexico", "Ohio", "Oklahoma", "Pennsylvania", "Pacific OCS", "Saskatchewan", "Texas", "Utah", "West Virginia", "Wyoming" ] }, "gold_well_tests": { "description": "One row per well test - initial potential, deliverability, surveys and retests - with tested oil, gas and water rates, gas-oil ratio as reported, flowing and shut-in pressures, and test duration. Test rates are short-duration measurements; monthly production is the sustained record.", "tier": "portal", "primary_key": [ "test_id" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "test_id", "type": "string", "nullable": false, "description": "Globally unique test identifier (opaque string) - this table's primary key. Never parse substrings out of it.\n", "enum": [] }, { "name": "well_id", "type": "string", "nullable": false, "description": "Join key to the well register. Always populated.\n", "enum": [] }, { "name": "test_date", "type": "date", "nullable": false, "description": "Date of the test. On shut-in status filings, the reported test date may be the filing's own effective month - the date the declared status takes effect - rather than a measured test's date.\n", "enum": [] }, { "name": "test_type", "type": "string", "nullable": true, "description": "Kind of test: initial_potential, survey, retest, or deliverability.\n", "enum": [ "initial_potential", "survey", "retest", "deliverability" ] }, { "name": "oil_per_day", "type": "float64", "nullable": true, "description": "Tested oil rate in BBL/d. Includes condensate for gas wells.\n", "enum": [] }, { "name": "gas_per_day", "type": "float64", "nullable": true, "description": "Tested gas rate in MCF/d.\n", "enum": [] }, { "name": "water_per_day", "type": "float64", "nullable": true, "description": "Tested water rate in BBL/d.\n", "enum": [] }, { "name": "gor", "type": "float64", "nullable": true, "description": "Gas-oil ratio in cubic feet of gas per barrel of oil (scf/bbl). The test form's own ratio where the form reports one; otherwise computed from the tested gas and oil rates (gas in cubic feet divided by oil in barrels).\n", "enum": [] }, { "name": "oil_gravity", "type": "float64", "nullable": true, "description": "Oil API gravity in degrees - a product quality indicator. Includes condensate for gas wells, so values above about 45 degrees are normal where the tested fluid is condensate rather than crude.\n", "enum": [] }, { "name": "gas_gravity", "type": "float64", "nullable": true, "description": "Specific gravity of the tested gas, relative to air = 1.0. Dry gas is near 0.6; richer gas carrying more heavy hydrocarbons runs higher, so this is a useful indicator of energy content per unit volume and of natural gas liquids richness. Note that inert gases such as carbon dioxide and nitrogen also raise specific gravity while lowering heating value, so a high value does not by itself mean rich gas.\n", "enum": [] }, { "name": "choke_size", "type": "int16", "nullable": true, "description": "Choke size in 64ths of an inch.\n", "enum": [] }, { "name": "flowing_pressure", "type": "int32", "nullable": true, "description": "Flowing wellhead pressure in psi.\n", "enum": [] }, { "name": "shut_in_pressure", "type": "int32", "nullable": true, "description": "Shut-in wellhead pressure in psi.\n", "enum": [] }, { "name": "producing_method", "type": "string", "nullable": true, "description": "Lift type during the test: flowing, pumping, gas_lift, plunger_lift, or esp (electric submersible pump).\n", "enum": [ "flowing", "pumping", "gas_lift", "plunger_lift", "esp" ] }, { "name": "test_duration_hours", "type": "int16", "nullable": true, "description": "Hours the well was tested.\n", "enum": [] }, { "name": "data_source", "type": "string", "nullable": true, "description": "Which source record the test came from (e.g. rrc_g10, ndic, ocd_well_detail, la_sonris_well_tests). Free text, not a fixed list - new values appear as regions are added.\n", "enum": [] } ], "regional_columns": [], "region_extras": { "bc": [ { "name": "wa_number", "type": "string", "description": "" }, { "name": "aofp_test_method", "type": "string", "description": "" } ], "la": [ { "name": "la_well_serial", "type": "string", "description": "" } ], "nd": [ { "name": "file_no", "type": "int64", "description": "" } ], "nm": [ { "name": "pool_id", "type": "string", "description": "" }, { "name": "pool_name", "type": "string", "description": "" } ], "ok": [ { "name": "completion_no", "type": "int32", "description": "" } ], "pa": [ { "name": "form_type", "type": "string", "description": "" }, { "name": "annular_pressure", "type": "int32", "description": "" } ], "tx": [ { "name": "well_identifier_id", "type": "string", "description": "" }, { "name": "district", "type": "string", "description": "" }, { "name": "lease_no", "type": "string", "description": "" }, { "name": "well_number", "type": "string", "description": "" }, { "name": "type_well", "type": "string", "description": "" }, { "name": "shut_in_month", "type": "date", "description": "Month the well was declared shut in. On statewide-query W-10 filings this is the filing's effective date, the month the declared status takes effect; on the W-10 tape feeds it is the RRC's own shut-in date field, the date the well was shut in or last utilized.\n" }, { "name": "sl_adjusted", "type": "boolean", "description": "" }, { "name": "sl_proxy", "type": "boolean", "description": "" } ] }, "serving_derived": [], "data_currency": [ { "region": "bc", "region_name": "British Columbia", "as_of": "2024-10-01", "customer_note": null }, { "region": "nd", "region_name": "North Dakota", "as_of": "2021-04-16", "customer_note": null } ], "regions_live": [ "bc", "la", "nd", "nm", "ok", "pa", "tx", "ut" ], "regions_live_names": [ "British Columbia", "Louisiana", "North Dakota", "New Mexico", "Oklahoma", "Pennsylvania", "Texas", "Utah" ] }, "gold_well_transporter": { "description": "Who moves and buys each well's production: one row per (well, product, role, counterparty, effective interval) linking wells to their gatherer, purchaser, or off-taker, with each counterparty's share of take where reported. Sourced from designation filings (Texas, Colorado, Louisiana) and realized off-take reports (New Mexico).", "tier": "portal", "primary_key": [ "well_id", "product", "role", "transporter_reg_id", "effective_from" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "well_id", "type": "string", "nullable": false, "description": "Join key to the well register (gold_wells): the well whose product this counterparty gathers, buys, or takes. Always populated.\n", "enum": [] }, { "name": "product", "type": "string", "nullable": false, "description": "The product stream, oil or gas (oil includes condensate). Part of the key, not an attribute: a well has distinct counterparties per stream.\n", "enum": [ "oil", "gas" ] }, { "name": "role", "type": "string", "nullable": false, "description": "The counterparty's role on this stream: gatherer = transports the product off-lease (physical takeaway); purchaser = the first buyer (marketing/credit); off_taker = the receiving counterparty where the source does not distinguish gatherer from purchaser. Texas designations split gatherer and purchaser (a company holding both roles appears as two rows); Colorado reports the hauler only (gatherer); New Mexico reports realized off-take (off_taker).\n", "enum": [ "gatherer", "purchaser", "off_taker" ] }, { "name": "transporter_reg_id", "type": "string", "nullable": false, "description": "The counterparty's regulator-issued ID: Texas RRC operator number, New Mexico OGRID, Colorado COGIS entity number. Always present; part of the key. Opaque string; combine with the well's region to look it up in gold_organization_registrations.\n", "enum": [] }, { "name": "transporter_entity_id", "type": "string", "nullable": true, "description": "The resolved company identifier for the counterparty (join to gold_organizations), the counterpart of operator_id on the well register. NULL until the counterparty is resolved; these are midstream and marketing companies (Energy Transfer, Enterprise, Plains, Targa), a different population than producers.\n", "enum": [] }, { "name": "transporter_name", "type": "string", "nullable": false, "description": "The counterparty's canonical display name (e.g. \"ENERGY TRANSFER COMPANY\", \"EAGLE FORD GATHERING LLC\"). Always present.\n", "enum": [] }, { "name": "effective_from", "type": "date", "nullable": false, "description": "Start of the counterparty's effective interval: the filed designation/effective date where the source files one (Texas, Colorado), or the first observed sale month where the source reports realized off-take without a filed date (New Mexico). For designations filed at lease level this is the filing's own start date, and it can be earlier than the well's arrival on the lease it was filed for. Part of the key.\n", "enum": [] }, { "name": "effective_to", "type": "date", "nullable": true, "description": "End of the interval. NULL means currently effective. Derived from the next superseding designation (the day before it takes effect) for filed sources, and for lease-replicated designations, the end of the well's tenure on the filed lease, whichever comes first; the last observed sale month for realized off-take.\n", "enum": [] }, { "name": "percent_of_take", "type": "float64", "nullable": true, "description": "The counterparty's share of the well's product stream, 0-100: the one magnitude comparable across the different source types. Observed on the Texas designation filing; derived for New Mexico (the counterparty's received volume over the well's total sold in the interval); NULL for Colorado (a designation with no volume) and wherever the source reports no share. Multiply by the disposition table's sold volume for the absolute flow to a counterparty.\n", "enum": [] }, { "name": "origin", "type": "string", "nullable": false, "description": "How the relationship was observed: reported_offtake = the counterparty actually received the volume (realized off-take, New Mexico); reported_designation = a filed designation at well grain (Colorado); lease_designated = a designation filed at lease level and applied to each of the lease's wells (Texas). A designation can sit unused; a realized off-take is an accounting fact: a real trader distinction. Always populated.\n", "enum": [ "reported_offtake", "reported_designation", "lease_designated" ] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "co", "la", "nm", "tx" ], "regions_live_names": [ "Colorado", "Louisiana", "New Mexico", "Texas" ] }, "gold_well_type_curves": { "description": "Stored type curves: for each cohort (basin-by-formation, plus coarser analog pools), the peak-normalized median decline shape by month-on-production with a p10/p90 donor-dispersion band. Scale a curve by a well's own peak to get that well's expected profile. The basin and region-analog curves are the ones that drive our new-well and total-supply projections; the two sub_region grains (model and descriptive) describe an area's own wells without feeding any projection. curve_grain, n_donors and is_extrapolated tell you the cohort grain, how many wells back the curve, and where the tail is extrapolated rather than donor-backed.", "tier": "portal", "primary_key": [ "atom_def_version", "curve_grain", "curve_key_hash", "stream", "mop" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "atom_def_version", "type": "string", "nullable": false, "description": "Version of the frozen cohort definition the curve was built over. Part of the primary key: a rebuild under a new cohort definition is a new curve, not a rewrite.\n", "enum": [] }, { "name": "curve_grain", "type": "string", "nullable": false, "description": "The grain of the cohort behind this curve: sub_region_formation (finest: subdivision x formation), sub_region_formation_descriptive (the same subdivision x formation cohort measured over ALL its wells: published for areas, typically low-rate stripper counties, whose representative-well pool is too thin for a model curve; descriptive of what the area's wells did, not an input to any forecast), basin_formation (basin x formation), region_analog (state/province x trajectory x stream, the coarsest same-region pool), cross_region_analog (a pool borrowed from an analog region). Coarser grains back wells whose own cohort is too thin.\n", "enum": [ "sub_region_formation", "sub_region_formation_descriptive", "basin_formation", "region_analog", "cross_region_analog" ] }, { "name": "curve_key_hash", "type": "string", "nullable": false, "description": "Stable identifier of the curve's cohort (opaque 12-character code), the curve id. Never parse it.\n", "enum": [] }, { "name": "stream", "type": "string", "nullable": false, "description": "'oil' | 'gas'. One curve per (grain, stream).", "enum": [ "oil", "gas" ] }, { "name": "mop", "type": "int16", "nullable": false, "description": "Month on production, starting at 1: the curve's x-axis.\n", "enum": [] }, { "name": "norm_rate", "type": "float64", "nullable": false, "description": "The cohort's median rate at this month, as a fraction of each well's own peak rate (each donor well is scaled by its own peak before the cohort median is taken; stored to 6 decimals). Multiply by a well's peak rate to get that well's expected profile. Between 0 and 1: the curve's maximum is typically below 1.0 because donors peak at different months. Not strictly declining in early months (the empirical median can rise for conventional and workover cohorts), but always declining in the terminal tail.\n", "enum": [] }, { "name": "norm_rate_p10", "type": "float64", "nullable": true, "description": "Optimistic band (petroleum convention, the higher normalized rate): the spread across the cohort's wells, not model error. NULL at months where too few wells report to define it.\n", "enum": [] }, { "name": "norm_rate_p90", "type": "float64", "nullable": true, "description": "Pessimistic band (petroleum convention, the lower normalized rate). NULL at months where too few wells report.\n", "enum": [] }, { "name": "is_extrapolated", "type": "bool", "nullable": false, "description": "False where enough cohort wells back this month of the curve; true where the value is extrapolated: before the first well-supported month (held flat) or past the last (the constant-decline tail).\n", "enum": [] }, { "name": "n_donors", "type": "int32", "nullable": false, "description": "Number of wells contributing to the curve. Constant per curve.\n", "enum": [] }, { "name": "terminal_decline_per_month", "type": "float64", "nullable": false, "description": "The constant monthly decline applied past the last well-supported month (bounded between 0.1% and 10% per month, so the tail always declines). Constant per curve.\n", "enum": [] }, { "name": "state_or_province", "type": "string", "nullable": false, "description": "The cohort's state or province (always present: region grain or finer).\n", "enum": [] }, { "name": "sub_region", "type": "string", "nullable": true, "description": "The administrative subdivision one level below state_or_province (US: county, disambiguated across states; Alberta/Saskatchewan: municipal district; Gulf of Mexico: protraction area). NULL except for curves at the sub_region_formation and sub_region_formation_descriptive grains, and NULL for country-modeled regions whose province or state is already the state_or_province axis.\n", "enum": [] }, { "name": "basin", "type": "string", "nullable": true, "description": "Cohort basin. NULL at the region_analog / cross_region_analog grains.\n", "enum": [] }, { "name": "trajectory_group", "type": "string", "nullable": false, "description": "'horizontal' | 'other'. Always present.", "enum": [] }, { "name": "sub_formation", "type": "string", "nullable": true, "description": "Cohort sub-formation. NULL where the cohort is not split by sub-formation.\n", "enum": [] }, { "name": "vintage_bucket", "type": "string", "nullable": true, "description": "The cohort's well-vintage grouping. NULL where the cohort is not split by vintage.\n", "enum": [] } ], "regional_columns": [], "region_extras": {}, "serving_derived": [], "data_currency": [], "regions_live": [ "ab", "ak", "al", "ar", "argentina", "bc", "brazil", "ca", "co", "gom", "ks", "la", "mb", "mexico", "ms", "mt", "nd", "nm", "oh", "ok", "pa", "sk", "tx", "ut", "wv", "wy" ], "regions_live_names": [ "Alberta", "Alaska", "Alabama", "Arkansas", "Argentina", "British Columbia", "Brazil", "California", "Colorado", "Gulf of Mexico", "Kansas", "Louisiana", "Manitoba", "Mexico", "Mississippi", "Montana", "North Dakota", "New Mexico", "Ohio", "Oklahoma", "Pennsylvania", "Saskatchewan", "Texas", "Utah", "West Virginia", "Wyoming" ] }, "gold_wells": { "description": "The master well register: one row per well, from the moment a drilling permit is approved through plugging. Carries identity, operators (current owner, as-reported, and the original driller), surface and bottom-hole location, key lifecycle dates (permit, spud, completion, first production, plugged), wellbore geometry (trajectory, depths, lateral length), formation, and status. Many attributes carry a paired _source column telling you where the value came from (reported by the source, measured from a directional survey, or derived). Regional columns add each jurisdiction's own subdivisions (county, district, municipal district, ...).", "tier": "portal", "primary_key": [ "well_id" ], "primary_key_exceptions": {}, "base_columns": [ { "name": "well_id", "type": "string", "nullable": false, "description": "Globally unique well identifier (opaque string), this table's primary key, and the join key every other well-grain table points at. Stable across time; never parse substrings out of it.\n", "enum": [] }, { "name": "national_well_id", "type": "string", "nullable": true, "description": "The well identifier issued by the jurisdiction, in its native format (US API number, Canadian UWI, and each country's equivalent). well_id is our stable global key; this is the number you would use at the source. For Canadian wells with several completion events, this is the UWI of the well's latest event.\n", "enum": [] }, { "name": "register_source", "type": "string", "nullable": true, "description": "How this well came to be in the register: current = the regulator's maintained well register lists it and we update it as the regulator does; legacy = a register or extract the publisher no longer maintains, so this record will not change; filing = a regulator filing (an approved, unexpired drilling permit) names the well and no register record exists yet; evidence = the regulator, or a regulator-mandated disclosure registry such as FracFocus, publishes facts about the well (production, completions, fracs, surveys) but no register record, so we carry a minimal header built from those facts. Populated once a region's register has been confirmed under this contract; empty until then.\n", "enum": [ "current", "legacy", "filing", "evidence" ] }, { "name": "country", "type": "string", "nullable": false, "description": "Country code (ISO 3166-1 alpha-2, upper-case, e.g. US, CA).\n", "enum": [] }, { "name": "state_province", "type": "string", "nullable": false, "description": "Full name of the state or province the well sits in (e.g. 'Texas', 'Alberta').\n", "enum": [] }, { "name": "state_province_code", "type": "string", "nullable": false, "description": "Jurisdiction code within the country (e.g. TX, AB); paired with country it forms a globally unique jurisdiction key.\n", "enum": [] }, { "name": "well_name", "type": "string", "nullable": true, "description": "Well name as designated by the operator, including the well number where the source provides it.\n", "enum": [] }, { "name": "operator", "type": "string", "nullable": true, "description": "The company operating this well today, as a canonical company name: mergers and acquisitions are applied as of today, so an acquired company's wells read the acquirer (XTO under ExxonMobil, Anadarko under Occidental). Sourced from the most recent operator on file (latest production report, else latest completion or permit), with ownership changes taking effect at deal closing, not announcement. Where this differs from reported_operator, our ownership graph is ahead of the source's operator-of-record.\n", "enum": [] }, { "name": "operator_id", "type": "string", "nullable": true, "description": "Stable company identifier for operator: the owner as of today. Join key to the organizations register (gold_organizations). NULL when the operator name cannot be resolved to a registered organization. Differs from reported_operator_id exactly where we corrected the source's stale record. For roll-ups by public company, group by this id and join gold_organizations for the ticker.\n", "enum": [] }, { "name": "operator_source", "type": "string", "nullable": false, "description": "How the current operator was determined, or why none is shown: production = the regulator's own operator-of-record for this well's production, brought to today through recorded acquisitions; well_record = the operator named on the well's regulatory record (where the name matches a company in our register, the company link is set; otherwise the name is shown as reported, without a link); well_record_succession = the record's operator followed through a recorded acquisition or merger to its current owner: the name shown can therefore differ from the name on the record; curated = the source publishes no operator, so the operator shown comes from our maintained mapping of the source's contracts and areas to companies; attribution_stale = the well last had a named operator so long before its latest reported activity that the source itself no longer supports that attribution: rather than show a likely-outdated company, none is shown; unresolved = a source names an operator for this well but we could not identify the company, so none is shown; unreported = no source names a real operator for this well. Always populated.\n", "enum": [ "production", "curated", "well_record", "well_record_succession", "attribution_stale", "unresolved", "unreported" ] }, { "name": "operator_registration_id", "type": "string", "nullable": true, "description": "The regulator-issued ID of the operator of record on the well record (TX P-5 number, ND operator number, AB AER licensee number, Brazil ANP CNPJ, and each region's equivalent): the raw regulator id, with no merger succession applied. May lag operator after an asset transfer, because the well record updates on the regulator's own schedule. Where the regulator issues licence IDs but never prints them on well records (currently Kansas), it is our match of the operator name to the state's licensee register, derived by us rather than filed. Opaque string; look it up in gold_organization_registrations together with the well's region. NULL otherwise.\n", "enum": [] }, { "name": "reported_operator", "type": "string", "nullable": true, "description": "The operator as the source records it today, normalized to a canonical display name but with NO merger succession applied: the faithful regulatory record. Equals operator except where our ownership graph corrected a stale operator-of-record at the source. NULL only where the source operator name is NULL.\n", "enum": [] }, { "name": "reported_operator_id", "type": "string", "nullable": true, "description": "Stable company identifier for reported_operator: the organization the source's name maps to, with no merger succession applied. Because it does not move when a company is later acquired, this is the stable id for joins and history. A company that renamed itself keeps one identifier: a rename is not a succession, so the as-filed name may differ from the identifier's current name. NULL when the raw name is not yet mapped to a registered organization. operator_id differing from reported_operator_id means we corrected the source's stale record.\n", "enum": [] }, { "name": "reported_operator_entity", "type": "string", "nullable": true, "description": "The raw operator name exactly as the source records it today (e.g. \"JALAPENO CORPORATION\", \"Solis Partners, L.L.C.\"): the audit-trail string before any normalization. NULL where the source gives no operator name, and where it names no real company: regulator placeholder strings (\"historic owner\", \"not assigned\") are treated as no operator rather than published as one.\n", "enum": [] }, { "name": "reported_operator_registration_id", "type": "string", "nullable": true, "description": "The regulator-issued operator ID for the well's reported operator, with no merger succession: currently identical to operator_registration_id (both carry the register-anchored value: source-printed where the regulator prints one, matched by name to the licensee register where it never does, currently Kansas). Carried so the reported_* column family reads the same across the well, production, and permit tables. NULL otherwise.\n", "enum": [] }, { "name": "original_operator", "type": "string", "nullable": true, "description": "The well's originating operator: the company that drilled and completed it, a historical fact with no merger succession applied. Distinct from reported_operator (the operator on the source's record today) and operator (the current owner after M&A). A best estimate from the earliest available signal: the regulator's own original-operator record, the earliest permit, the first entry in the regulator's change-of-operator register, or the first month of production; original_operator_source says which one determined it for this well. Currently carried as the raw source name, without normalization.\n", "enum": [] }, { "name": "original_operator_id", "type": "string", "nullable": true, "description": "Stable company identifier for the originating operator (the driller), with no merger succession applied. Because a driller's id never moves when its parent is later acquired, this is the churn-free key for grouping wells by who drilled them. Where no distinct driller record exists yet, it equals reported_operator_id; the two diverge as driller-specific sources land region by region. NULL when the name cannot be resolved to a registered organization or original_operator is NULL. Distinct from operator_id (current owner) and reported_operator_id (the source's record today).\n", "enum": [] }, { "name": "original_operator_entity", "type": "string", "nullable": true, "description": "The raw originating-operator name before any normalization: the audit-trail string for the driller. Currently equal to original_operator; where a region gains a driller-specific source, this keeps the driller's raw name while reported_operator_entity keeps the current source name. NULL exactly when original_operator is NULL.\n", "enum": [] }, { "name": "original_operator_registration_id", "type": "string", "nullable": true, "description": "The regulator-issued registration id of the ORIGINAL (driller) operator: the driller's register lookup key, the counterpart of operator_registration_id (current owner) and reported_operator_registration_id (source-of-record today). Sourced from the same row that supplied the driller name (a permit's operator number, or the register interval that named the operator of record), so it is present only where a region re-sources the driller AND an id can be anchored to that same record: printed on it, or, where the regulator never prints licence IDs (currently Kansas), matched by name to the state's licensee register. Where the well has no distinct driller it falls back to operator_registration_id, the same company's id, except where the operator name itself comes from our own curated mapping rather than a source-printed name; there no source registration id is inherited. Honest-NULL otherwise: never the current operator's id on a well whose driller was somebody else. It exists so a future company-record correction can re-resolve the driller by direct register lookup rather than by re-deriving it from source filings.\n", "enum": [] }, { "name": "original_operator_source", "type": "string", "nullable": true, "description": "Which source determined original_operator on this well, from highest to lowest confidence: drilling = the regulator's own original-operator record; permit = the operator on the earliest permit (the closest driller proxy where no native record exists); transfer_register = the earliest operator of record in the regulator's change-of-operator (or licensee transfer) register: the company holding the well before its first recorded transfer. Treat it as a bound rather than a measurement: it is the earliest operator the register knows, and how close that is to the driller depends on when the register itself begins, so a well drilled long before the register was digitized may sit several unrecorded transfers away. first_production = the operator in the well's earliest production month; existing = a value carried over from before this sourcing existed: in some regions effectively the driller, in others the current operator of record, so treat it as lower confidence. For analysis that needs verified drillers, filter to drilling, permit, transfer_register, or first_production. NULL exactly when original_operator is NULL.\n", "enum": [ "drilling", "permit", "transfer_register", "first_production", "existing" ] }, { "name": "latitude", "type": "float64", "nullable": true, "description": "Surface hole location latitude (WGS84 decimal degrees). Completions and other well-grain tables don't carry coordinates: join them to this table via well_id. Bottom-hole coordinates sit on this same row (bhl_latitude / bhl_longitude).\n", "enum": [] }, { "name": "longitude", "type": "float64", "nullable": true, "description": "Surface hole location longitude (WGS84 decimal degrees).\n", "enum": [] }, { "name": "coordinate_source", "type": "string", "nullable": true, "description": "Where the surface coordinates (latitude/longitude) came from: gis = an agency GIS point layer (most accurate); dls_centroid = a Canadian legal-subdivision cell centroid, an estimate, not a surveyed point; plss_centroid = the US equivalent, a PLSS-section centroid estimate validated into the well's county, with co-located wells spread apart so they don't stack (a section is 1 square mile, so accuracy is roughly plus or minus 0.5 mile); the section's centre is taken from the surveyed section boundary where we hold it, otherwise from other wells we hold in that section. NULL where coordinate provenance is not tracked for that region, or the well has no surface coordinates; always set together with latitude.\n", "enum": [ "gis", "dls_centroid", "plss_centroid" ] }, { "name": "bhl_latitude", "type": "float64", "nullable": true, "description": "Bottom-hole location latitude (WGS84), best-determined: resolved from the well's available bottom-hole sources in a fixed precedence, best first. NULL where no source reports one, or where the reported point lies implausibly far from the surface location, or is only a restatement of it; see bhl_source for the ranking and which source won.\n", "enum": [] }, { "name": "bhl_longitude", "type": "float64", "nullable": true, "description": "Bottom-hole location longitude (WGS84), best-determined. Resolved with bhl_latitude: the pair always comes from the same record; see bhl_source for which source won.\n", "enum": [] }, { "name": "bhl_source", "type": "string", "nullable": true, "description": "Where bhl_latitude/bhl_longitude came from, in precedence order (best first): survey = an as-drilled directional-survey toe (most accurate); reported = a post-drill operator-reported bottom hole (completion filings and similar); footage_call = computed by us from the filing's own bottom-hole footage call (the stated distances from the section lines), anchored on the well's surface location or, where the filing's two footage calls name different sections, on a corner derived from the surveyed boundary of the section named in the bottom-hole call: an estimate, typically within a few hundred feet of a surveyed toe and occasionally thousands, less precise than a surveyed toe; plat = a coordinate we extracted from a filed well plat (a digitized drawing point, scale-limited); survey_planned = a survey toe from a pre-drill plan or a survey not yet confirmed as-drilled (approximate; gold_directional_surveys.is_proposed carries each survey's plan-vs-as-drilled classification); permit = the permit's proposed target; gis = the agency's published GIS bottom hole (a digitization of the permitted target where one was filed), used only where no other source supplies one. A post-drill reported location outranks a pre-drill planned survey. NULL when both bottom-hole coordinates are NULL.\n", "enum": [ "survey", "reported", "footage_call", "plat", "survey_planned", "permit", "gis" ] }, { "name": "kop_latitude", "type": "float64", "nullable": true, "description": "Kickoff-point latitude (WGS84), best-determined: the point where the wellbore departs vertical and begins its build toward the lateral, resolved from the well's available kickoff-point sources in a fixed precedence, best first. NULL where no source reports one; see kop_source for the ranking and which source won.\n", "enum": [] }, { "name": "kop_longitude", "type": "float64", "nullable": true, "description": "Kickoff-point longitude (WGS84), best-determined. Resolved with kop_latitude: the pair always comes from the same record; see kop_source for which source won.\n", "enum": [] }, { "name": "kop_source", "type": "string", "nullable": true, "description": "Where kop_latitude/kop_longitude came from, in precedence order (best first): survey = derived from an as-drilled directional survey (most accurate); reported = a stated kickoff point in a post-drill filing (New Mexico's C-102 take-point form and similar); footage_call = computed by us from the filing's own stated distances from the section lines, anchored on the well's surface location; plat = a coordinate we extracted from a filed well plat (a digitized drawing point, scale-limited); survey_planned = from a pre-drill plan or a survey not yet confirmed as-drilled; permit = the permit's proposed point; gis = an agency-published GIS layer. NULL when both kickoff-point coordinates are NULL.\n", "enum": [ "survey", "reported", "footage_call", "plat", "survey_planned", "permit", "gis" ] }, { "name": "landing_latitude", "type": "float64", "nullable": true, "description": "Landing-point latitude (WGS84), best-determined: where the wellbore levels off and the lateral begins (the heel); for take-point sources this is the first take point of the completed interval. Resolved from the well's available landing-point sources in a fixed precedence, best first. NULL where no source reports one; see landing_source for the ranking and which source won.\n", "enum": [] }, { "name": "landing_longitude", "type": "float64", "nullable": true, "description": "Landing-point longitude (WGS84), best-determined. Resolved with landing_latitude: the pair always comes from the same record; see landing_source for which source won.\n", "enum": [] }, { "name": "landing_source", "type": "string", "nullable": true, "description": "Where landing_latitude/landing_longitude came from, in precedence order (best first): survey = derived from an as-drilled directional survey (most accurate); reported = a stated landing or first-take point in a post-drill filing (New Mexico's C-102 take-point form and similar); footage_call = computed by us from the filing's own stated distances from the section lines, anchored on the well's surface location; plat = a coordinate we extracted from a filed well plat (a digitized drawing point, scale-limited); survey_planned = from a pre-drill plan or a survey not yet confirmed as-drilled; permit = the permit's proposed point; gis = an agency-published GIS layer. NULL when both landing-point coordinates are NULL.\n", "enum": [ "survey", "reported", "footage_call", "plat", "survey_planned", "permit", "gis" ] }, { "name": "basin", "type": "string", "nullable": true, "description": "Geologic province the well sits in: a sedimentary basin for roughly 90% of wells, a structural province such as a platform, arch, or uplift for the rest; never a play name. Assigned from AAPG/GHGRP polygons in the US, CER in Canada, and regulator-reported values elsewhere. Published names are our canonical vocabulary: usually the assigning source's own province name, sometimes a documented spelling correction or a commercial merge of adjacent provinces (North Central Texas), and sometimes an established short form (WCSB).\n", "enum": [] }, { "name": "sub_basin", "type": "string", "nullable": true, "description": "Structural sub-unit of the basin, populated only where a real named sub-unit exists (Midland Basin, Delaware Basin, Eastern Overthrust Area), never a play name. NULL otherwise.\n", "enum": [] }, { "name": "field", "type": "string", "nullable": true, "description": "Field or pool designation as assigned by the source's regulator, in the source's own naming. Where the regulator publishes none, a region may carry a documented, per-well-validated assignment derived from the source's own vocabulary.\n", "enum": [] }, { "name": "permit_filed_date", "type": "date", "nullable": true, "description": "Filing date of the well's drilling-permit application. Can postdate permit_approved_date.\n", "enum": [] }, { "name": "permit_approved_date", "type": "date", "nullable": true, "description": "Date of the well's earliest drilling-permit approval: the point at which a well enters this register.\n", "enum": [] }, { "name": "spud_date", "type": "date", "nullable": true, "description": "Date drilling began.\n", "enum": [] }, { "name": "completion_date", "type": "date", "nullable": true, "description": "Date the well was completed per the regulatory filing (e.g. Texas W-2/G-1). The initial completion only: later recompletions live in gold_well_completions.\n", "enum": [] }, { "name": "first_production_date", "type": "date", "nullable": true, "description": "First day of the first calendar month with hydrocarbon production (oil or gas above zero). Derived from production data, or, where the regulator itself publishes the well's first-production date and it predates our production history, from that reported date; always month precision (the 1st of the month). For wells present at the start of a region's series, this is the series' first month rather than a verified start for the well; see first_production_is_censored.\n", "enum": [] }, { "name": "first_production_day", "type": "date", "nullable": true, "description": "Estimated actual first day of production, at day precision: derived from the first month's producing days (month end minus producing days, plus one), or taken from the regulator's own reported first-production date where its day precision passed validation and no derived value exists. NULL when it cannot be determined. For wells present at the start of a region's series, this is the series' first month rather than a verified start for the well; see first_production_is_censored.\n", "enum": [] }, { "name": "first_production_is_censored", "type": "boolean", "nullable": true, "description": "True where first_production_date marks the start of our source's production history for the region rather than a verified start for this well.\n", "enum": [] }, { "name": "plugged_date", "type": "date", "nullable": true, "description": "Date the well was plugged. Reflects current state: set when the well is plugged, cleared back to NULL if the well is reopened.\n", "enum": [] }, { "name": "trajectory", "type": "string", "nullable": true, "description": "Wellbore trajectory: horizontal, vertical, or directional. Survey-first: where the well's directional surveys give a confident verdict, that overrides the agency-reported well type; otherwise the agency value is used. See trajectory_source for which source won. NULL where not available.\n", "enum": [ "horizontal", "vertical", "directional" ] }, { "name": "trajectory_source", "type": "string", "nullable": true, "description": "Which source determined trajectory on this well: survey = derived from an as-drilled directional survey (authoritative: overrides the agency field); survey_planned = derived from a planned or proposed survey only, where no as-drilled lateral was filed (lower confidence); reported = the operator- or agency-reported well type (well header, completion record, or permit: the default); permit = the permit application's planned orientation, where that application is the only orientation record we hold - usually a well not yet drilled, sometimes a drilled well with no as-drilled report (regions still carrying permit-planned values under reported re-tag them as they rebuild); inferred = derived from an indirect signal such as a workover flag, a production flag, or a well-name/code convention (lowest confidence). NULL exactly when trajectory is NULL.\n", "enum": [ "survey", "survey_planned", "reported", "permit", "inferred" ] }, { "name": "primary_product", "type": "string", "nullable": true, "description": "Whether the well is primarily an oil or a gas well. Production-first: determined from the well's first-year production gas-oil ratio wherever it has production (at or below 6 MCF per BBL reads oil; Texas uses 15): ground truth that wins over any classification. For wells without production: the regulator's own classification where it has proven reliable; in regions reported at producing-unit grain, the unit's gas-oil ratio; otherwise our calibrated estimate from the well's location, depth, era and neighbouring wells (the product of the play it was drilled in), made only where it clears the region's measured agreement bar against the regulator's own classification. See primary_product_source for which. NULL where no signal clears the bar, and for service wells (injection, disposal, storage, observation, service, stratigraphic test, see well_purpose) with no product evidence of their own: a service well never receives an estimated product, but one with its own production history or regulator product classification, typically a well converted after producing, keeps it.\n", "enum": [ "oil", "gas" ] }, { "name": "primary_product_source", "type": "string", "nullable": true, "description": "Which signal determined primary_product on this well, from highest to lowest confidence: production_gor = the first-year production gas-oil ratio (ground truth: wins for every well with production); agency_lease_type = the regulator's oil-lease vs gas-well lease classification; agency_well_type = a regulator well-type, well-class or reservoir-fluid classification mapped to oil or gas; agency_permit = oil or gas from the permit record; unit_production_gor = the gas-oil ratio of the producing unit the well belongs to, in regions reported at unit grain rather than per well; inferred = our calibrated estimate from location, depth, era and neighbouring wells, made only where it clears the region's measured accuracy bar (published on the methodology page). Agency and inferred values appear only where production could not decide. NULL exactly when primary_product is NULL.\n", "enum": [ "production_gor", "agency_lease_type", "agency_well_type", "agency_permit", "unit_production_gor", "inferred" ] }, { "name": "well_purpose", "type": "string", "nullable": true, "description": "The well's function: producer, injector, disposal, observation, storage, service, stratigraphic_test, or other. Same values as gold_well_permits. NULL = the source is silent on purpose; other = the source states a purpose outside this list.\n", "enum": [ "producer", "injector", "disposal", "observation", "storage", "service", "stratigraphic_test", "other" ] }, { "name": "is_dry_hole", "type": "boolean", "nullable": true, "description": "True where the regulator recorded the well as a dry hole: drilled and found no producible hydrocarbons. False where the regulator's well record says otherwise; NULL where the source publishes no dry-hole outcome for the well. A dry hole's well record states no operating purpose, so its well_purpose is NULL except where a region's permit register supplies the permitted class; its primary_product, if present, is the play's product marked inferred.\n", "enum": [] }, { "name": "well_status", "type": "string", "nullable": true, "description": "The well's lifecycle status: permitted, cancelled (the permit expired or was withdrawn before drilling; no well was drilled under it), drilling, duc (drilled, uncompleted), completed, producing, shut_in, plugged, or abandoned. Not a pass-through of the agency's status field: resolved by precedence across two signal families, our own lifecycle facts (production activity, plugging records, key dates) and the agency-reported status. See well_status_source for which signal won. NULL where no signal of any kind resolves.\n", "enum": [ "permitted", "cancelled", "drilling", "duc", "completed", "producing", "shut_in", "plugged", "abandoned" ] }, { "name": "well_status_source", "type": "string", "nullable": true, "description": "Which signal determined well_status: production (production activity), plugged_record (a plugging record), agency_reported (the agency's reported status), completion_date, spud_date, or permit_date (the corresponding lifecycle date). NULL where status provenance is not yet tracked for that region, or where well_status itself is NULL.\n", "enum": [ "production", "plugged_record", "agency_reported", "completion_date", "spud_date", "permit_date" ] }, { "name": "is_offshore", "type": "boolean", "nullable": true, "description": "Whether the well is offshore, as the source classifies it: stored as reported, not derived from coordinates.\n", "enum": [] }, { "name": "formation", "type": "string", "nullable": true, "description": "Best-available name of the geologic unit the well is completed in or targets: for producers the producing formation; for injection, disposal, storage, and service wells the completed or permitted reservoir, normalized to a canonical play-level vocabulary. May come from operator reporting, from survey-based determination against formation-top evidence (the well's own confirmed tops or our formation surfaces), or from the surface model alone; see formation_method for which. Pragmatic naming: a value may be a geological group, a formation, or an age.\n", "enum": [] }, { "name": "zone", "type": "string", "nullable": true, "description": "Best-available landing zone within the formation, a generic term covering benches, members, sands, and intervals. May come from the source's own reporting or from survey-based determination against the well's confirmed formation tops; see zone_method for which, and zone_reported for what was reported before any determination of ours. Sub-zone detail is carried in the value itself (e.g. \"a_upper\").\n", "enum": [] }, { "name": "zone_reported", "type": "string", "nullable": true, "description": "The zone attributable to the source: what the operator or a regulatory filing gave, normalized to our vocabulary, captured before any determination of ours could refine or replace it, so you can always tell our contribution from theirs. Unlike formation_reported, this is the normalized value, not the raw filing text. Populated exactly where zone_method is 'reported', and NULL everywhere else, so zone_method tells you, per well, whether the zone we publish came from the source at all.\n", "enum": [] }, { "name": "zone_method", "type": "string", "nullable": true, "description": "How zone was determined: reported = the source reported it (including a zone read from a regulatory well-file document); survey = determined from the well's directional survey read against its own confirmed formation tops; well_name = parsed from a zone code in the well name. NULL wherever zone is NULL.\n", "enum": [ "reported", "survey", "well_name" ] }, { "name": "formation_reported", "type": "string", "nullable": true, "description": "The raw reported formation (uppercased, trimmed): the original filing text before normalization, always preserved so you can verify our normalization and flag issues. Where the well filed a formation or pool code rather than a name, this is the source's own register label for that code, verbatim: the label behind the formation we publish, which for a well with several completion events is the event that supplied it and need not be the event whose pool code the well's other columns carry. Populated even when formation is NULL (unmatched or junk values). NULL where no source string exists behind the value: a value we computed ourselves (a parse or extraction of a source string) or a third-party geological-survey pick (see formation_method = stratigraphic_pick), never appears here.\n", "enum": [] }, { "name": "formation_method", "type": "string", "nullable": true, "description": "How formation was determined: reported = derived from source-reported formation or pool information (normalization, decoding, or selection between reported values may apply); survey = determined or verified from the well's directional survey read against formation-top evidence (the well's own confirmed formation tops, or our formation surface model); modeled = filled from the surface model alone, without a survey; stratigraphic_pick = assigned from the deepest published stratigraphic pick on this wellbore: a third-party geological-survey pick rather than an operator declaration, and an estimate of the deepest formation penetrated rather than a declared target or producing formation. The zone column carries its own provenance: see zone_method.\n", "enum": [ "reported", "survey", "modeled", "stratigraphic_pick" ] }, { "name": "formation_id", "type": "string", "nullable": true, "description": "Canonical stratigraphic-unit identifier: the join key to the formations register (gold_formations), which adds the geological backbone (hierarchy, stratigraphic order, external references) beneath the pragmatic formation/zone strings. Resolved from the well's formation and basin. NULL for formation names not yet mapped to the registry. Opaque string. Never parse it.\n", "enum": [] }, { "name": "elevation_kb", "type": "int32", "nullable": true, "description": "Best determination of surface elevation in feet, nominally kelly bushing (KB) datum, used for subsea depth (TVDSS = elevation_kb - TVD). Validated against terrain-model ground elevation: the operator value is kept when the two agree, and replaced or filled from the terrain model when wrong or missing: see elevation_kb_source for which won. Note: most sources report ground-based elevations, so values are effectively ground + ~11 ft; true rig-floor KB from directional surveys (~+40 ft) is preferred where available. The ~30 ft systematic offset is small relative to formation thickness but matters for bench-level work. For bare-earth ground elevation see elevation_gl.\n", "enum": [] }, { "name": "elevation_kb_reported", "type": "int32", "nullable": true, "description": "The raw operator-reported elevation (feet), converted to the KB datum where the source reports ground level (+12 ft) or derrick floor (+1 ft). Always preserved for transparency. NULL when the source has no elevation. May differ from elevation_kb where terrain-model validation corrected or filled the value.\n", "enum": [] }, { "name": "elevation_kb_source", "type": "string", "nullable": true, "description": "Which tier determined elevation_kb on this well, from highest to lowest confidence: survey = true rig-floor KB from a directional survey (~40 ft above ground, most accurate); reported = the operator/agency value, kept after agreeing with the terrain model or where no terrain data covers the well (effectively ground + ~11 ft for most sources); dem_estimated = no usable source value, estimated as terrain-model ground + 11 ft: the +11 ft is a fleet-wide median, not a per-well measurement, so treat these as low confidence. NULL exactly when elevation_kb is NULL.\n", "enum": [ "survey", "reported", "dem_estimated" ] }, { "name": "elevation_gl", "type": "int32", "nullable": true, "description": "Ground-level (bare-earth) elevation in feet: the true natural surface, distinct from elevation_kb (the rig-referenced drilling datum). Operator-reported native ground elevation where the source supplies it (e.g. New Mexico, Colorado); elsewhere sampled per well from terrain models (USGS 3DEP in the US, Copernicus GLO-30 internationally). NULL only where the well has no coordinates, no covering terrain tile, and no operator ground value (e.g. offshore).\n", "enum": [] }, { "name": "tvd", "type": "int32", "nullable": true, "description": "True vertical depth to the producing zone, in feet: the deepest true vertical depth reached by any of the well's bores. Best-determined: a validated reported TVD, else the directional-survey depth, else, for a vertical well, the well's total depth (TVD equals TD exactly for verticals). Every candidate is validated (TVD at or below MD, plausible bounds) before it lands. See tvd_source for which source won.\n", "enum": [] }, { "name": "tvd_source", "type": "string", "nullable": true, "description": "Which source determined tvd on this well: reported = an operator- or agency-reported TVD (the most common); survey = rolled up from the well's as-drilled directional survey (deepest station); survey_planned = rolled up from a planned or proposed survey (lower confidence); td_vertical = the well's total depth used as TVD for a vertical well (exact for verticals; where only a planned permit depth exists, the value is a pre-drill estimate); bhl_geometric = computed geometrically from measured depth and the surface-to-bottom-hole displacement for a barely-deviated well; permit = the permit's proposed vertical depth, the lowest-confidence tier, used only where nothing else exists. NULL exactly when tvd is NULL.\n", "enum": [ "reported", "survey", "survey_planned", "td_vertical", "bhl_geometric", "permit" ] }, { "name": "md", "type": "int32", "nullable": true, "description": "Total measured depth along the wellbore, surface to total depth, in feet. For a well with several bores, the deepest hole drilled.\n", "enum": [] }, { "name": "md_source", "type": "string", "nullable": true, "description": "Which source determined md on this well: reported = a regulator well-header or completion total depth; survey = the as-drilled directional survey's deepest measured depth; survey_planned = a planned survey's depth; permit = the permit's proposed depth. NULL exactly when md is NULL.\n", "enum": [ "reported", "survey", "survey_planned", "permit" ] }, { "name": "lateral_length", "type": "int32", "nullable": true, "description": "Lateral length in feet. Four different quantities share this column, and lateral_length_source says which one a row carries. Where a completed-length source exists (perforated interval, treated interval, or operator-reported) it wins and the value is the completed lateral; otherwise the drilled lateral measured along a quality-checked directional survey; otherwise, where only a planned trajectory is on file, its length, which the well may not have been drilled to; otherwise a geometric estimate of the drilled lateral (mapped wellbore path, perforation take-points, heel-to-toe or surface-to-bottom-hole distance calibrated against the region's own reported and surveyed laterals, or measured depth minus vertical depth). A completed length is never overridden by a geometric one, because it is legitimately shorter than the drilled lateral; a quality-checked survey overrides a geometric value that is clearly degenerate, or fills a missing one. A geometric estimate stands where no survey we can use is on file, or where the survey we hold is so much shorter than the estimate that we read it as missing its toe. Group or filter on lateral_length_source before comparing lengths across wells. NULL for vertical wells.\n", "enum": [] }, { "name": "lateral_length_source", "type": "string", "nullable": true, "description": "Which source determined lateral_length on this well. Completed length, meaning what was perforated or stimulated, legitimately shorter than the drilled lateral and never overridden by a survey: perf_interval = the perforated or completed interval (preferred); treatment = the stimulated interval; operator_reported = a single reported length. Measured drilled path: survey = the directional survey's along-hole length from heel to toe. Planned rather than as-drilled: survey_planned = the same from a planned survey, for a well that may not have been drilled to it (lower confidence). Geometric estimates of the drilled lateral, which stand where no survey we can use is on file, ranked by accuracy from wellpath_polyline, then take_point and heel_toe_geodesic together, then surface_bhl_geodesic, then md_minus_tvd: wellpath_polyline = the arc length of the mapped wellbore path; take_point = the straight-line distance between the first and last perforation take-points, which excludes the build section; heel_toe_geodesic = the straight line between the lateral's heel and toe; surface_bhl_geodesic = the straight-line surface-to-bottom-hole distance, using the bottom hole bhl_source records for the well (for some wells a proposed rather than drilled location), calibrated against the region's own reported and surveyed laterals (uncalibrated it includes the build-section step-out); md_minus_tvd = measured depth minus vertical depth, which overstates the lateral because the build section counts as lateral. A build-section correction is subtracted from md_minus_tvd: fitted on the region's own surveys where it holds enough of them, otherwise the typical value measured across the regions that do. May differ from the latest completion's lateral_length_source where the survey overrode a degenerate geometric value. NULL exactly when lateral_length is NULL.\n", "enum": [ "perf_interval", "treatment", "survey", "survey_planned", "wellpath_polyline", "take_point", "heel_toe_geodesic", "surface_bhl_geodesic", "operator_reported", "md_minus_tvd" ] } ], "regional_columns": [ { "name": "abstract", "type": "string", "description": "Texas abstract number.", "regions": [ "tx" ] }, { "name": "block", "type": "string", "description": "Subdivision within larger area. TX: survey block. GOM: OCS lease block. Future offshore: concession block.\n", "regions": [ "ecuador", "gom", "pacific", "tx" ] }, { "name": "county", "type": "string", "description": "County name (parish in Louisiana). Oklahoma: Osage County's oil and gas are regulated by the BIA Osage Agency, not the OCC: those wells are included in the register; filter county = 'OSAGE' (county_fips 40113) to separate them from the OCC-regulated subset.", "regions": [ "ak", "al", "ar", "ca", "co", "ks", "la", "mi", "ms", "mt", "nd", "nm", "oh", "ok", "pa", "tx", "ut", "wv", "wy" ] }, { "name": "county_fips", "type": "string", "description": "5-digit STATEFP+COUNTYFP (canonical FIPS GEOID).", "regions": [ "ak", "al", "ar", "ca", "co", "ks", "la", "mi", "ms", "mt", "nd", "nm", "oh", "ok", "pa", "tx", "ut", "wv", "wy" ] }, { "name": "county_unique", "type": "string", "description": "Disambiguated county for cross-state grouping. Pre-computed against the full US national county list (~3,100). Unique names stay clean (Reeves), ambiguous names get suffix (Washington (PA)).\n", "regions": [ "ak", "al", "ar", "ca", "co", "ks", "la", "mi", "ms", "mt", "nd", "nm", "oh", "ok", "pa", "tx", "ut", "wv", "wy" ] }, { "name": "district", "type": "string", "description": "Regulatory district. TX = RRC district (1-10, 7B, 7C, 8A, 9). NM = OCD district.", "regions": [ "ca", "la", "tx" ] }, { "name": "lease_name", "type": "string", "description": "Regulatory lease name. TX: RRC lease name. NM: OCD lease. ND: NDIC lease. OK: OCC lease. Also used to construct well_name. Not applicable in Canada (no lease concept) or GOM (OCS lease block in block column).\n", "regions": [ "ca", "ks", "nd", "ok", "pa", "tx" ] }, { "name": "legal_subdivision", "type": "string", "description": "Dominion Land Survey legal subdivision.", "regions": [ "ab", "bc", "mb", "sk" ] }, { "name": "meridian", "type": "string", "description": "Principal or reference meridian of the survey grid, in the source's own designation: the fleet carries several forms because the surveys do. DLS (AB/SK/MB): a bare digit, the Nth meridian west of the Principal Meridian (AB 4/5/6; SK 1/2/3; MB 1); a location east of the Principal Meridian cannot be expressed in this convention and publishes no grid. US PLSS: the state's own designation, which may be an ordinal (CO `6` = the Sixth Principal Meridian), a code (OK `IM`/`CM`), a name (AK `Umiat`, `Seward`) or a bare letter (LA `W`/`E`, published verbatim; Louisiana publishes no decode for them). Because both systems use a bare digit, the same digit means different things in different regions, and a bare letter is the meridian designation, not the direction letter inside range: LA meridian `W` beside range `15W` are two different statements. The well's region tells you which form applies.\n", "regions": [ "ab", "ak", "bc", "co", "la", "mb", "ok", "sk", "ut" ] }, { "name": "municipal_district", "type": "string", "description": "Census subdivision containing the well's surface location, as Statistics Canada names it: a municipality, or an area treated as a municipal equivalent. Mostly the rural unit: an Alberta municipal district, county, specialized municipality, improvement district or special area, or a Saskatchewan rural municipality. A well inside another unit, such as a city, town, village, First Nations reserve or unorganized territory, carries that unit instead. Two different units can share a name.", "regions": [ "ab", "sk" ] }, { "name": "municipality", "type": "string", "description": "Named civil subdivision of the county in which the well is located: a township, borough, village or city, in the regulator's own naming. The level below county; not a survey grid cell (see township).\n", "regions": [ "oh", "pa" ] }, { "name": "nts_block", "type": "string", "description": "Block letter of the well's surface location within its NTS map area.", "regions": [ "bc" ] }, { "name": "nts_map_area", "type": "string", "description": "BCER NTS map sheet designation for the well's surface location (e.g. 094-A-15).", "regions": [ "bc" ] }, { "name": "nts_quarter_unit", "type": "string", "description": "Quarter-unit letter of the well's surface location in the National Topographic System grid (BC's survey system outside the Peace River DLS block).", "regions": [ "bc" ] }, { "name": "nts_unit", "type": "string", "description": "Unit number of the well's surface location within its NTS block.", "regions": [ "bc" ] }, { "name": "ocd_district", "type": "string", "description": "New Mexico Oil Conservation Division district number.", "regions": [ "nm" ] }, { "name": "oil_sands_area", "type": "string", "description": "Alberta Energy Regulator oil sands area the well is located in: Athabasca, Cold Lake, Peace River Area 1 or Peace River Area 2, as Petrinex reports it. Empty for wells outside a designated oil sands area.", "regions": [ "ab" ] }, { "name": "property_id", "type": "string", "description": "NM OCD property/case identifier. Groups wells on a regulatory property.", "regions": [ "nm" ] }, { "name": "protraction_area", "type": "string", "description": "OCS protraction area full name (e.g., Mississippi Canyon).", "regions": [ "gom", "pacific" ] }, { "name": "quarter", "type": "string", "description": "The legal-subdivision (aliquot) chain within the section, finest-first, as single-space-separated tokens of variable depth: `NE SW` = the NE quarter OF the SW quarter; `N2 SE` = the north half of the SE quarter. Tokens: quarters `NE`/`NW`/`SE`/`SW` (each dividing its parent by 4), halves `N2`/`S2`/`E2`/`W2` (dividing by 2), and `C` = centre: alone, the centre of the section; heading a chain (`C SE SE`) or fused to a call (`CNE`, `CN2`), the centre of the subdivision it names; a centre call is a point, not an acreage. In a well-formed chain the first token is the finest call and the last the coarsest, and depth is the number of tokens (`NE` = 160 acres, `NE SW` = 40, `N2 SE` = 80). Government lot and tract calls are kept as the source states them, with any internal space closed up so the space stays the token separator (`LOT 5` becomes `LOT5`; `LOT4`, `LT15`), and are not aliquot subdivisions. Empty where the source stated no subdivision or an unreadable one, and where a chain's coarsest call is missing (a fine call alone would mislead); where only a finer call was unreadable, the coarser chain is published. Lettered tract systems (e.g. New Mexico unit letters A-P) are not aliquots and never appear here; a lettered tract is translated to its chain where the map is verified, with the raw letter kept as a region-specific column.\n", "regions": [ "co", "mi", "mt", "nd", "nm", "ok", "ut", "wy" ] }, { "name": "range", "type": "string", "description": "Survey range of the well's surface location (PLSS and DLS). PLSS format: ``, no space, no zero-pad, e.g. `13E`, `95W`; the direction is always present. PLSS half-ranges likewise: `13.5W`. DLS format (AB/SK/MB): bare unpadded integer. The direction is carried by the meridian, not the range.\n", "regions": [ "ab", "al", "ar", "bc", "ca", "co", "ks", "la", "mb", "mi", "ms", "mt", "nd", "nm", "ok", "sk", "ut", "wy" ] }, { "name": "regional_district", "type": "string", "description": "BC regional district.", "regions": [ "bc" ] }, { "name": "section", "type": "string", "description": "~1 sq mile parcel of the well's surface location, in the survey system's own designation. Universal across survey systems. Usually a bare integer with no zero-pad and no decimal (`17`, not `17.00` or `017`) and normally 1..36, though irregular or special surveys can legitimately exceed 36. Some states publish a designation that is not a number at all: Texas publishes surveyed half-sections (`34 1/2`) and lot-block calls (`LB10`) where the original survey was not laid out in numbered sections.\n", "regions": [ "ab", "al", "ar", "bc", "ca", "co", "ks", "la", "mb", "mi", "ms", "mt", "nd", "nm", "ok", "sk", "tx", "ut", "wy" ] }, { "name": "survey", "type": "string", "description": "Texas survey name (e.g., T&P RR CO).", "regions": [ "tx" ] }, { "name": "township", "type": "string", "description": "Survey township of the well's SURFACE location (PLSS and DLS), the same point latitude/longitude describe. PLSS format: ``, no space, no zero-pad, e.g. `17N`, `152N`; the direction is always present (T9N and T9S are ~100 miles apart), so a bare PLSS number is left NULL. PLSS half-townships keep their fraction: `33.5N` is a real surveyed township, distinct from both `33N` and `34N`. DLS format (AB/SK/MB): bare unpadded integer, e.g. `16`. DLS townships number north from the 49th parallel and carry no direction. A region whose land is not laid out in a rectangular survey (PLSS or DLS) publishes no township: an original-survey township number that is only meaningful inside its own survey district is not a value this column can carry.\n", "regions": [ "ab", "al", "ar", "bc", "ca", "co", "ks", "la", "mb", "mi", "ms", "mt", "nd", "nm", "ok", "sk", "ut", "wy" ] }, { "name": "water_depth_category", "type": "string", "description": "Shelf, Deepwater, Ultra-deep.", "regions": [ "gom", "pacific" ] }, { "name": "well_pad", "type": "string", "description": "Well pad name or identifier. Groups co-located wells on a single surface pad.", "regions": [ "pa" ] } ], "region_extras": { "ab": [ { "name": "licence_number", "type": "string", "description": "" }, { "name": "field_code", "type": "string", "description": "" }, { "name": "pool_code", "type": "string", "description": "The source's pool code for the well's latest completion event, including administrative pseudo-pools such as commingled or temporary codes that name no single formation." }, { "name": "drilling_completion_date", "type": "date", "description": "Date the drilling operations to reach the well's total depth were completed: Petrinex's Finished Drill Date for the well, from the Alberta Well Infrastructure file." } ], "ak": [ { "name": "geo_area_code", "type": "string", "description": "" }, { "name": "unit_code", "type": "string", "description": "" }, { "name": "water_depth", "type": "int32", "description": "" } ], "ar": [ { "name": "ar_well_key", "type": "string", "description": "" }, { "name": "ar_permit_no", "type": "string", "description": "" } ], "argentina": [ { "name": "resource_type", "type": "string", "description": "" }, { "name": "resource_subtype", "type": "string", "description": "" }, { "name": "project", "type": "string", "description": "" }, { "name": "concession", "type": "string", "description": "" } ], "bc": [ { "name": "wa_number", "type": "string", "description": "" }, { "name": "formation_code", "type": "string", "description": "" }, { "name": "area_code", "type": "string", "description": "" } ], "brazil": [ { "name": "installation", "type": "string", "description": "" }, { "name": "well_category", "type": "string", "description": "" }, { "name": "water_depth", "type": "int32", "description": "" }, { "name": "pre_salt", "type": "boolean", "description": "" } ], "ca": [ { "name": "area_name", "type": "string", "description": "" } ], "co": [ { "name": "field_code", "type": "string", "description": "" }, { "name": "facility_id", "type": "string", "description": "" } ], "colombia": [ { "name": "contrato", "type": "string", "description": "" }, { "name": "municipio", "type": "string", "description": "" }, { "name": "lahee_class", "type": "string", "description": "" } ], "ecuador": [ { "name": "rig", "type": "string", "description": "" }, { "name": "well_classification", "type": "string", "description": "" }, { "name": "td_date", "type": "date", "description": "" }, { "name": "drilling_end_date", "type": "date", "description": "" } ], "gom": [ { "name": "water_depth", "type": "int32", "description": "" }, { "name": "area_code", "type": "string", "description": "" }, { "name": "total_depth_date", "type": "date", "description": "Date this borehole reached total depth, as reported by BOEM" } ], "guyana": [ { "name": "oil_block", "type": "string", "description": "" }, { "name": "water_depth", "type": "int32", "description": "" }, { "name": "fluid_type", "type": "string", "description": "" }, { "name": "well_slug", "type": "string", "description": "" } ], "ks": [ { "name": "lease_kid", "type": "string", "description": "" }, { "name": "n_workovers", "type": "int32", "description": "" } ], "la": [ { "name": "la_well_serial", "type": "string", "description": "" } ], "mb": [ { "name": "licence_number", "type": "string", "description": "" }, { "name": "field_code", "type": "string", "description": "" }, { "name": "pool_code", "type": "string", "description": "" }, { "name": "mineral_rights", "type": "string", "description": "" } ], "nd": [ { "name": "file_no", "type": "int64", "description": "" } ], "nm": [ { "name": "lease_type", "type": "string", "description": "" }, { "name": "footage_ns", "type": "string", "description": "" }, { "name": "footage_ew", "type": "string", "description": "" }, { "name": "ocd_unit_letter", "type": "string", "description": "New Mexico's lettered unit/tract code for the well's location within its section (NMOCD 16-cell lettering, A-P), exactly as the source publishes it. Not a PLSS aliquot: see quarter.\n" } ], "pa": [ { "name": "unconventional", "type": "boolean", "description": "" } ], "pacific": [ { "name": "water_depth", "type": "int32", "description": "" }, { "name": "area_code", "type": "string", "description": "" }, { "name": "total_depth_date", "type": "date", "description": "Date this borehole reached total depth, as reported by BOEM" } ], "sk": [ { "name": "licence_number", "type": "string", "description": "" }, { "name": "field_code", "type": "string", "description": "" }, { "name": "pool_code", "type": "string", "description": "" }, { "name": "drilling_completion_date", "type": "date", "description": "Date the drilling operations to reach the well's total depth were completed: Petrinex's Finished Drill Date for the well, from the Saskatchewan Well Infrastructure file." } ], "tx": [ { "name": "n_completions", "type": "int32", "description": "Number of completion events recorded for this well (its row count in gold_well_completions; 0 where none is on file)" } ], "ut": [ { "name": "lease_type", "type": "string", "description": "" }, { "name": "surface_owner", "type": "string", "description": "" }, { "name": "footage_ns", "type": "string", "description": "" }, { "name": "footage_ew", "type": "string", "description": "" } ], "wv": [ { "name": "quad", "type": "string", "description": "" }, { "name": "tax_district", "type": "string", "description": "" } ] }, "serving_derived": [], "data_currency": [], "regions_live": [ "ab", "ak", "al", "ar", "argentina", "bc", "brazil", "ca", "co", "colombia", "ecuador", "gom", "guyana", "ks", "la", "mb", "mexico", "mi", "ms", "mt", "nd", "nm", "oh", "ok", "pa", "pacific", "sk", "tx", "ut", "wv", "wy" ], "regions_live_names": [ "Alberta", "Alaska", "Alabama", "Arkansas", "Argentina", "British Columbia", "Brazil", "California", "Colorado", "Colombia", "Ecuador", "Gulf of Mexico", "Guyana", "Kansas", "Louisiana", "Manitoba", "Mexico", "Michigan", "Mississippi", "Montana", "North Dakota", "New Mexico", "Ohio", "Oklahoma", "Pennsylvania", "Pacific OCS", "Saskatchewan", "Texas", "Utah", "West Virginia", "Wyoming" ] } } }