{
    "version":"0.1.0",
    "id":"retrieve-biodiversity-data",
    "use_case":"BOKU",
    "title":"Retrieve biodiversity data from the web",
    "description":"This process retrieves biodiveryity data, i.e. occurrences for various species, from the sources GBIF, iNaturalist and VertNet. For more details, please ask BOKU.",
    "jobControlOptions":[
        "sync-execute",
        "async-execute"
    ],
    "keywords":[
        "pan-european use case",
        "AquaINFRA",
        "R"
    ],
    "links":[
        {
            "type":"text/html",
            "rel":"about",
            "title":"GitHub repo",
            "href":"https://github.com/AnthonyBasooma/specleanr",
            "hreflang":"en-US"
        },
        {
            "type":"application/json",
            "rel":"self",
            "href":"https://aquainfra.ogc.igb-berlin.de/pygeoapi/processes/retrieve-biodiversity-data?f=json",
            "title":"Process description as JSON",
            "hreflang":"en-US"
        },
        {
            "type":"text/html",
            "rel":"alternate",
            "href":"https://aquainfra.ogc.igb-berlin.de/pygeoapi/processes/retrieve-biodiversity-data?f=html",
            "title":"Process description as HTML",
            "hreflang":"en-US"
        },
        {
            "type":"text/html",
            "rel":"http://www.opengis.net/def/rel/ogc/1.0/job-list",
            "href":"https://aquainfra.ogc.igb-berlin.de/pygeoapi/jobs?f=html",
            "title":"Jobs list as HTML",
            "hreflang":"en-US"
        },
        {
            "type":"application/json",
            "rel":"http://www.opengis.net/def/rel/ogc/1.0/job-list",
            "href":"https://aquainfra.ogc.igb-berlin.de/pygeoapi/jobs?f=json",
            "title":"Jobs list as JSON",
            "hreflang":"en-US"
        },
        {
            "type":"application/json",
            "rel":"http://www.opengis.net/def/rel/ogc/1.0/execute",
            "href":"https://aquainfra.ogc.igb-berlin.de/pygeoapi/processes/retrieve-biodiversity-data/execution?f=json",
            "title":"Execution for this process as JSON",
            "hreflang":"en-US"
        }
    ],
    "inputs":{
        "species_names_list":{
            "title":"Species names to download (list of species)",
            "description":"List of species. If you have a url to the dataset, use the option below.",
            "schema":{
                "type":"string"
            },
            "minOccurs":0,
            "maxOccurs":1,
            "keywords":[]
        },
        "species_names_url":{
            "title":"Data with species names to download",
            "description":"URL to a table containing the occurrences from any source. This can be the outcome of the match-data process.",
            "schema":{
                "type":"string"
            },
            "minOccurs":0,
            "maxOccurs":1,
            "keywords":[
                "csv"
            ]
        },
        "colname_species":{
            "title":"Species column name",
            "description":"If the data provided in the data path is a dataframe, indicate here the column name with species names.",
            "schema":{
                "type":"string"
            },
            "minOccurs":0,
            "maxOccurs":1,
            "keywords":[
                "string"
            ]
        },
        "databases":{
            "title":"Database names",
            "description":"List of databases to consider. Only \"gbif, inat, vertnet\" supported.",
            "schema":{
                "type":"array"
            },
            "minOccurs":1,
            "maxOccurs":1,
            "keywords":[
                "databases"
            ]
        },
        "gbif_limit":{
            "title":"Max number (GBIF)",
            "description":"The maximum number of data points that are being retrieved from GBIF.",
            "schema":{
                "type":"integer"
            },
            "minOccurs":0,
            "maxOccurs":1,
            "keywords":[]
        },
        "inaturalist_limit":{
            "title":"Max number (iNaturalist)",
            "description":"The maximum number of data points that are being retrieved from iNaturalist.",
            "schema":{
                "type":"integer"
            },
            "minOccurs":0,
            "maxOccurs":1,
            "keywords":[]
        },
        "vertnet_limit":{
            "title":"Max number (VertNet)",
            "description":"The maximum number of data points that are being retrieved from VertNet.",
            "schema":{
                "type":"integer"
            },
            "minOccurs":0,
            "maxOccurs":1,
            "keywords":[]
        },
        "study_area_bbox":{
            "title":"Area of Interest as a bounding box",
            "description":"A bounding box: {'bbox': [south, west, north, east]} (see https://docs.ogc.org/is/18-062r2/18-062r2.html#bounding-box-value)",
            "schema":{
                "type":"object"
            },
            "minOccurs":0,
            "maxOccurs":1,
            "keywords":[
                "OGC BBOX"
            ]
        },
        "study_area_shapefile":{
            "title":"Area of Interest as shapefile",
            "description":"URL to the zipped input shapefile containing the study areas inside which you would like to retrieve occurrences.",
            "schema":{
                "type":"string"
            },
            "minOccurs":0,
            "maxOccurs":1,
            "keywords":[
                "shapefile"
            ]
        },
        "study_area_geojson_url":{
            "title":"Area of Interest as GeoJSON",
            "description":"URL to the input GeoJSON file containing the study areas inside which you would like to retrieve occurrences.",
            "schema":{
                "type":"string"
            },
            "minOccurs":0,
            "maxOccurs":1,
            "keywords":[
                "JSON",
                "GeoJSON"
            ]
        },
        "study_area_geojson":{
            "title":"Area of Interest as a GeoJSON object",
            "description":"Directly post the GeoJSON containing the study areas inside which you would like to retrieve occurrences.",
            "schema":{
                "type":"object"
            },
            "minOccurs":0,
            "maxOccurs":1,
            "keywords":[
                "JSON",
                "GeoJSON"
            ]
        },
        "percentage_correctness":{
            "title":"Species name correctness in percent",
            "description":"A number indicating the percentage of species name correctness that should be allowed to be replaced. High values ensure a perfect match from the standard database.",
            "schema":{
                "type":"number"
            },
            "minOccurs":0,
            "maxOccurs":1,
            "keywords":[
                "percentagecorrectness"
            ]
        },
        "synonym_check":{
            "title":"Consider synonyms from standard databases like FishBase",
            "description":"YES, if synoymns species names should be returned from FishBase during data checks before data download.",
            "schema":{
                "type":"boolean"
            },
            "minOccurs":1,
            "maxOccurs":1,
            "keywords":[
                "synonym"
            ]
        }
    },
    "outputs":{
        "biodiversity_data":{
            "title":"Combined occurrences",
            "description":"A table containing the combined occurrences inside the study area.",
            "schema":{
                "type":"object",
                "contentMediaType":"application/json"
            }
        }
    },
    "example":{
        "inputs":{
            "input_data":"Squalius cephalus, Salmo trutta, Thymallus thymallus, Anguilla anguilla",
            "study_area_bbox":{
                "bbox":[
                    42.08333,
                    8.1525,
                    50.245,
                    29.73583
                ]
            },
            "databases":[
                "gbif",
                "inat",
                "vertnet"
            ],
            "gbif_limit":50,
            "vertnet_limit":50,
            "inaturalist_limit":50,
            "percentage_correctness":30,
            "synonym_check":true
        }
    },
    "outputTransmission":[
        "value"
    ]
}