{
"id": "app.gainforest.dwc.occurrence",
"defs": {
"main": {
"key": "tid",
"type": "record",
"record": {
"type": "object",
"required": [
"basisOfRecord",
"scientificName",
"eventDate",
"createdAt"
],
"properties": {
"sex": {
"enum": [
"male",
"female",
"hermaphrodite"
],
"type": "string",
"description": "The sex of the biological individual(s).",
"maxGraphemes": 64
},
"class": {
"type": "string",
"description": "The full scientific name of the class.",
"maxGraphemes": 128
},
"genus": {
"type": "string",
"description": "The full scientific name of the genus.",
"maxGraphemes": 128
},
"order": {
"type": "string",
"description": "The full scientific name of the order.",
"maxGraphemes": 128
},
"county": {
"type": "string",
"description": "The full, unabbreviated name of the next smaller administrative region than stateProvince.",
"maxGraphemes": 256
},
"dcType": {
"enum": [
"PhysicalObject",
"StillImage",
"MovingImage",
"Sound",
"Text",
"Event",
"Dataset"
],
"type": "string",
"description": "The Dublin Core type class that best describes the resource (dc:type).",
"maxGraphemes": 64
},
"family": {
"type": "string",
"description": "The full scientific name of the family.",
"maxGraphemes": 128
},
"phylum": {
"type": "string",
"description": "The full scientific name of the phylum or division.",
"maxGraphemes": 128
},
"country": {
"type": "string",
"description": "The name of the country or major administrative unit.",
"maxGraphemes": 128
},
"eventID": {
"type": "string",
"description": "Identifier for the sampling event. Can be used to group occurrences from the same event.",
"maxGraphemes": 256
},
"habitat": {
"type": "string",
"description": "A description of the habitat in which the event occurred (e.g., 'tropical rainforest', 'mangrove swamp', 'montane cloud forest').",
"maxGraphemes": 512
},
"kingdom": {
"type": "string",
"description": "The full scientific name of the kingdom (e.g., 'Animalia', 'Plantae', 'Fungi').",
"maxGraphemes": 128
},
"license": {
"type": "string",
"description": "A legal document giving official permission to do something with the record. Recommended: a Creative Commons URI (e.g., 'http://creativecommons.org/licenses/by/4.0/').",
"maxGraphemes": 512
},
"behavior": {
"type": "string",
"description": "The behavior shown by the subject at the time of occurrence (e.g., 'foraging', 'nesting', 'roosting').",
"maxGraphemes": 256
},
"eventRef": {
"type": "string",
"format": "at-uri",
"description": "AT-URI reference to an app.gainforest.dwc.event record (for star-schema linkage)."
},
"locality": {
"type": "string",
"description": "The specific description of the place (e.g., '500m upstream of bridge on Rio Pará').",
"maxGraphemes": 1024
},
"createdAt": {
"type": "string",
"format": "datetime",
"description": "Timestamp of record creation in the ATProto PDS."
},
"eventDate": {
"type": "string",
"description": "The date or date-time (or interval) during which the occurrence was recorded. ISO 8601 format (e.g., '2024-03-15', '2024-03-15T10:30:00Z', '2024-03/2024-06').",
"maxGraphemes": 64
},
"eventTime": {
"type": "string",
"description": "The time of the event. ISO 8601 format (e.g., '14:30:00', '14:30:00+02:00').",
"maxGraphemes": 64
},
"lifeStage": {
"type": "string",
"description": "The age class or life stage at the time of occurrence (e.g., 'adult', 'juvenile', 'larva', 'seedling', 'sapling').",
"maxGraphemes": 128
},
"taxonRank": {
"enum": [
"kingdom",
"phylum",
"class",
"order",
"family",
"subfamily",
"genus",
"subgenus",
"species",
"subspecies",
"variety",
"form"
],
"type": "string",
"description": "The taxonomic rank of the most specific name in scientificName.",
"maxGraphemes": 64
},
"fieldNotes": {
"type": "string",
"description": "Notes or reference to notes taken in the field about the event.",
"maxGraphemes": 10000
},
"locationID": {
"type": "string",
"description": "Identifier for the location (e.g., a reference to a named site).",
"maxGraphemes": 256
},
"recordedBy": {
"type": "string",
"description": "Person(s) responsible for recording the occurrence in the field. Pipe-delimited for multiple (e.g., 'Jane Smith | John Doe').",
"maxGraphemes": 512
},
"references": {
"type": "string",
"format": "uri",
"description": "A related resource that is referenced, cited, or otherwise pointed to by the record (URL)."
},
"countryCode": {
"type": "string",
"maxLength": 2,
"minLength": 2,
"description": "The standard code for the country (ISO 3166-1 alpha-2)."
},
"datasetName": {
"type": "string",
"description": "The name identifying the dataset from which the record was derived.",
"maxGraphemes": 256
},
"gbifTaxonKey": {
"type": "string",
"description": "GBIF backbone taxonomy key for the identified taxon. Retained for backward compatibility with existing GainForest workflows.",
"maxGraphemes": 64
},
"identifiedBy": {
"type": "string",
"description": "Person(s) who assigned the taxon to the occurrence. Pipe-delimited for multiple.",
"maxGraphemes": 512
},
"municipality": {
"type": "string",
"description": "The full, unabbreviated name of the next smaller administrative region than county.",
"maxGraphemes": 256
},
"occurrenceID": {
"type": "string",
"description": "A globally unique identifier for the occurrence record. Recommended: a persistent URI (e.g., DOI, LSID, or UUID-based URI).",
"maxGraphemes": 256
},
"recordedByID": {
"type": "string",
"description": "Persistent identifier(s) (e.g., ORCID) of the person(s) who recorded. Pipe-delimited for multiple.",
"maxGraphemes": 512
},
"rightsHolder": {
"type": "string",
"description": "Person or organization owning or managing rights over the resource.",
"maxGraphemes": 256
},
"basisOfRecord": {
"enum": [
"HumanObservation",
"MachineObservation",
"PreservedSpecimen",
"LivingSpecimen",
"FossilSpecimen",
"MaterialSample",
"MaterialEntity",
"MaterialCitation"
],
"type": "string",
"description": "The specific nature of the data record. Must be one of the Darwin Core class names.",
"maxGraphemes": 64
},
"geodeticDatum": {
"type": "string",
"description": "The spatial reference system for the coordinates. Recommended: 'EPSG:4326' (WGS84).",
"maxGraphemes": 64
},
"mediaEvidence": {
"ref": "app.gainforest.common.defs#smallImage",
"type": "ref",
"description": "Direct image evidence uploaded as ATProto blob (photo of organism, camera trap image, etc.)."
},
"stateProvince": {
"type": "string",
"description": "The name of the next smaller administrative region than country.",
"maxGraphemes": 256
},
"collectionCode": {
"type": "string",
"description": "The name, acronym, or code identifying the collection or dataset from which the record was derived.",
"maxGraphemes": 256
},
"dateIdentified": {
"type": "string",
"description": "The date on which the identification was made. ISO 8601 format.",
"maxGraphemes": 64
},
"identifiedByID": {
"type": "string",
"description": "Persistent identifier(s) (e.g., ORCID) of the person(s) who identified. Pipe-delimited.",
"maxGraphemes": 512
},
"samplingEffort": {
"type": "string",
"description": "The amount of effort expended during the event (e.g., '2 trap-nights', '30 minutes', '10 km transect').",
"maxGraphemes": 256
},
"scientificName": {
"type": "string",
"description": "The full scientific name, with authorship and date if known (e.g., 'Centropyge flavicauda Fraser-Brunner 1933').",
"maxGraphemes": 512
},
"vernacularName": {
"type": "string",
"description": "A common or vernacular name for the taxon.",
"maxGraphemes": 256
},
"associatedMedia": {
"type": "string",
"description": "Identifiers (URIs) of media associated with the occurrence. Pipe-delimited for multiple.",
"maxGraphemes": 2048
},
"decimalLatitude": {
"type": "string",
"description": "Geographic latitude in decimal degrees (WGS84). Positive values are north of the Equator. Range: -90 to 90.",
"maxGraphemes": 32
},
"individualCount": {
"type": "integer",
"minimum": 0,
"description": "The number of individuals present at the time of the occurrence."
},
"institutionCode": {
"type": "string",
"description": "The name or acronym of the institution having custody of the object(s) or information in the record.",
"maxGraphemes": 256
},
"locationRemarks": {
"type": "string",
"description": "Comments about the location.",
"maxGraphemes": 2048
},
"specificEpithet": {
"type": "string",
"description": "The name of the species epithet of the scientificName.",
"maxGraphemes": 128
},
"taxonomicStatus": {
"type": "string",
"description": "The status of the use of the scientificName (e.g., 'accepted', 'synonym', 'doubtful').",
"maxGraphemes": 64
},
"decimalLongitude": {
"type": "string",
"description": "Geographic longitude in decimal degrees (WGS84). Positive values are east of the Greenwich Meridian. Range: -180 to 180.",
"maxGraphemes": 32
},
"occurrenceStatus": {
"enum": [
"present",
"absent"
],
"type": "string",
"description": "Statement about the presence or absence of a taxon at a location.",
"maxGraphemes": 64
},
"organismQuantity": {
"type": "string",
"description": "A number or enumeration value for the quantity of organisms (e.g., '27', '12.5', 'many').",
"maxGraphemes": 64
},
"samplingProtocol": {
"type": "string",
"description": "The method or protocol used during the event (e.g., 'camera trap', 'point count', 'mist net', '20m x 20m plot survey', 'acoustic monitoring').",
"maxGraphemes": 1024
},
"verbatimLocality": {
"type": "string",
"description": "The original textual description of the place as provided by the recorder.",
"maxGraphemes": 1024
},
"dynamicProperties": {
"type": "string",
"description": "Additional structured data as a valid JSON string (per Simple DwC Section 7.1). Example: '{\"iucnStatus\":\"vulnerable\",\"canopyCover\":\"85%\"}'. Should be flattened to a single line with no non-printing characters.",
"maxGraphemes": 10000
},
"nomenclaturalCode": {
"enum": [
"ICZN",
"ICN",
"ICNP",
"ICTV",
"BioCode"
],
"type": "string",
"description": "The nomenclatural code under which the scientificName is constructed.",
"maxGraphemes": 64
},
"occurrenceRemarks": {
"type": "string",
"description": "Comments or notes about the occurrence.",
"maxGraphemes": 5000
},
"associatedSequences": {
"type": "string",
"description": "Identifiers (URIs) of genetic sequence information associated with the occurrence. Pipe-delimited for multiple.",
"maxGraphemes": 2048
},
"dataGeneralizations": {
"type": "string",
"description": "A description of actions taken to make the data less specific or complete (e.g., 'coordinates rounded to nearest 0.1 degree').",
"maxGraphemes": 1024
},
"informationWithheld": {
"type": "string",
"description": "A description of what information is withheld from this record and why (e.g., 'coordinates generalized to protect endangered species').",
"maxGraphemes": 1024
},
"associatedReferences": {
"type": "string",
"description": "Identifiers (URIs) of literature associated with the occurrence. Pipe-delimited for multiple.",
"maxGraphemes": 2048
},
"higherClassification": {
"type": "string",
"description": "A complete list of taxa names terminating at the rank immediately superior to the taxon. Pipe-delimited (e.g., 'Animalia|Chordata|Mammalia|Rodentia|Ctenomyidae|Ctenomys').",
"maxGraphemes": 1024
},
"infraspecificEpithet": {
"type": "string",
"description": "The name of the lowest or terminal infraspecific epithet.",
"maxGraphemes": 128
},
"maximumDepthInMeters": {
"type": "integer",
"minimum": 0,
"description": "The greater depth of a range of depth below the local surface (in meters)."
},
"minimumDepthInMeters": {
"type": "integer",
"minimum": 0,
"description": "The lesser depth of a range of depth below the local surface (in meters)."
},
"organismQuantityType": {
"type": "string",
"description": "The type of quantification system used for organismQuantity (e.g., 'individuals', '% biomass', 'stems/ha').",
"maxGraphemes": 128
},
"associatedOccurrences": {
"type": "string",
"description": "Identifiers of other occurrences associated with this one (e.g., parasite-host). Pipe-delimited.",
"maxGraphemes": 2048
},
"identificationRemarks": {
"type": "string",
"description": "Comments or notes about the identification.",
"maxGraphemes": 2048
},
"reproductiveCondition": {
"type": "string",
"description": "The reproductive condition at the time of occurrence (e.g., 'flowering', 'fruiting', 'budding', 'pregnant').",
"maxGraphemes": 128
},
"identificationQualifier": {
"type": "string",
"description": "A brief phrase or standard term qualifying the identification (e.g., 'cf. agrestis', 'aff. agrestis').",
"maxGraphemes": 256
},
"previousIdentifications": {
"type": "string",
"description": "Previous assignments of names to the occurrence. Pipe-delimited.",
"maxGraphemes": 2048
},
"maximumElevationInMeters": {
"type": "integer",
"description": "The upper limit of the range of elevation (in meters above sea level)."
},
"minimumElevationInMeters": {
"type": "integer",
"description": "The lower limit of the range of elevation (in meters above sea level)."
},
"scientificNameAuthorship": {
"type": "string",
"description": "The authorship information for the scientific name (e.g., 'Fraser-Brunner 1933').",
"maxGraphemes": 256
},
"coordinateUncertaintyInMeters": {
"type": "integer",
"minimum": 1,
"description": "Horizontal distance (meters) from the given coordinates describing the smallest circle containing the whole location."
}
}
},
"description": "A biodiversity occurrence record following the Simple Darwin Core standard. Each record represents one occurrence of an organism at a location and time."
}
},
"$type": "com.atproto.lexicon.schema",
"lexicon": 1,
"description": "A single biodiversity occurrence record aligned with Simple Darwin Core (TDWG Standard 450, version 2023-09-13). Represents one organism or group of organisms at a particular place and time."
}