{
  "name": "BotanAI plant data layer",
  "description": "Open, downloadable, provenance-tagged bulk dumps of the botanai.app plant corpus. Every fact carries a source, a date and a licence. Free to reuse under the licences listed per source; attribution required where a source requires it.",
  "site": "https://botanai.app",
  "homepage": "https://botanai.app/data/",
  "schema_version": 1,
  "generated": "2026-07-20",
  "species_documented": 56125,
  "license": {
    "corpus_record": "CC BY 4.0",
    "attribution": "BotanAI, https://botanai.app",
    "note": "Each record and dump line assembled by BotanAI is offered under CC BY 4.0. The underlying FACTS are governed by their own source licence, listed per source in sources[] and per field in data-dictionary.json. Where a source is CC BY, attribute it. Where a source is CC0 or public domain, attribution is appreciated but not required. Photographs (on the per-species .json sibling) are licensed individually; CC BY-SA images are marked derivatives_restricted and must not be cropped or composited. No NonCommercial data is included in these dumps."
  },
  "data_dictionary": "https://botanai.app/data/data-dictionary.json",
  "machine_readable_surface": {
    "per_species_json": "https://botanai.app/plants/{slug}.json",
    "facets": "https://botanai.app/plants/facets.json",
    "search_index": "https://botanai.app/search/head.json",
    "note": "Every species page has a .json sibling (rel=\"alternate\"). CORS is open on those."
  },
  "sources": [
    {
      "key": "wfo",
      "name": "World Flora Online Plant List",
      "license": "CC0 1.0",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "attribution": "World Flora Online (2026). worldfloraonline.org",
      "url": "https://www.worldfloraonline.org/",
      "provides": "Accepted names, authorities, synonymy, family and genus placement."
    },
    {
      "key": "kew_wcvp",
      "name": "Kew, World Checklist of Vascular Plants (WCVP v16)",
      "license": "CC BY 3.0",
      "license_url": "https://creativecommons.org/licenses/by/3.0/",
      "attribution": "Govaerts R (ed.). 2026. WCVP. Facilitated by the Royal Botanic Gardens, Kew. doi.org/10.15468/6h8ucr",
      "url": "https://doi.org/10.15468/6h8ucr",
      "provides": "Native range (TDWG level-3 botanical countries; introduced/extinct/doubtful excluded) and life form."
    },
    {
      "key": "chelsa",
      "name": "CHELSA V2.1",
      "license": "CC0 1.0",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "attribution": "Karger, D.N. et al. (2017). Climatologies at high resolution for the earth's land surface areas. Scientific Data 4, 170122.",
      "url": "https://chelsa-climate.org/",
      "provides": "The climate envelope: 5th to 95th percentile of conditions at georeferenced observations of a species."
    },
    {
      "key": "kew_useful",
      "name": "Kew, World Checklist of Useful Plant Species (2020)",
      "license": "CC BY 4.0",
      "license_url": "https://creativecommons.org/licenses/by/4.0/",
      "attribution": "Diazgranados M et al. (2020). World Checklist of Useful Plant Species. Royal Botanic Gardens, Kew. doi.org/10.5063/F1CV4G34",
      "url": "https://doi.org/10.5063/F1CV4G34",
      "provides": "Documented use categories (uses dimension)."
    },
    {
      "key": "duke",
      "name": "Dr. Duke's Phytochemical and Ethnobotanical Database",
      "license": "CC0 1.0",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "attribution": "U.S. Department of Agriculture, Agricultural Research Service. doi.org/10.15482/USDA.ADC/1239279",
      "url": "https://doi.org/10.15482/USDA.ADC/1239279",
      "provides": "Notable compounds and their reported biological activities (phytochemistry dimension)."
    },
    {
      "key": "iucn_wikidata",
      "name": "IUCN Red List category, via Wikidata (P141)",
      "license": "CC0 1.0 (Wikidata carrier; the category is a factual label)",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "attribution": "IUCN Red List category, carried through Wikidata (wikidata.org). Assessment: IUCN.",
      "url": "https://www.wikidata.org/",
      "provides": "Conservation status (conservation dimension)."
    },
    {
      "key": "names",
      "name": "Vernacular names, Wikidata (P1843) and GBIF",
      "license": "CC0 1.0 / per source",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "attribution": "Wikidata (wikidata.org, CC0) and GBIF vernacular names (gbif.org).",
      "url": "https://www.wikidata.org/",
      "provides": "Names in other languages, grouped by language (vernacular_names dimension)."
    },
    {
      "key": "globi",
      "name": "Global Biotic Interactions (GloBI)",
      "license": "CC BY 4.0 (aggregate)",
      "license_url": "https://creativecommons.org/licenses/by/4.0/",
      "attribution": "Poelen, J.H. et al. (2014). Global Biotic Interactions. globalbioticinteractions.org",
      "url": "https://www.globalbioticinteractions.org",
      "provides": "Recorded ecological interactions (interactions dimension). Provenance asserted at the GloBI aggregate level."
    },
    {
      "key": "ipni",
      "name": "IPNI (International Plant Names Index)",
      "license": "CC BY 4.0",
      "license_url": "https://creativecommons.org/licenses/by/4.0/",
      "attribution": "International Plant Names Index (2026). ipni.org. The Royal Botanic Gardens Kew, Harvard University Herbaria & Australian National Botanic Gardens.",
      "url": "https://www.ipni.org",
      "provides": "The protologue: author, work, year and IPNI record for each name (nomenclature dimension)."
    },
    {
      "key": "usda",
      "name": "USDA PLANTS Database",
      "license": "Public domain (US Government work)",
      "license_url": "https://plants.usda.gov/",
      "attribution": "USDA, NRCS. The PLANTS Database. plants.usda.gov",
      "url": "https://plants.usda.gov/",
      "provides": "Structured growth traits, the base slice of the merged growth_traits dimension, and some common names."
    },
    {
      "key": "gift",
      "name": "GIFT (Global Inventory of Floras and Traits)",
      "license": "CC BY 4.0",
      "license_url": "https://creativecommons.org/licenses/by/4.0/",
      "attribution": "Weigelt P, Konig C, Kreft H (2020). GIFT, a Global Inventory of Floras and Traits. Journal of Biogeography 47.",
      "url": "https://gift.uni-goettingen.de/",
      "provides": "Woodiness, life form, succulence, photosynthetic pathway, height and flowering months, worldwide (growth_traits dimension)."
    },
    {
      "key": "wikidata_traits",
      "name": "Wikidata structured plant traits (P4000, P2048)",
      "license": "CC0 1.0",
      "license_url": "https://creativecommons.org/publicdomain/zero/1.0/",
      "attribution": "Wikidata (wikidata.org, CC0).",
      "url": "https://www.wikidata.org/",
      "provides": "Structured fruit type (P4000) and a small CC0 set of structured heights (P2048) in the growth_traits dimension."
    },
    {
      "key": "eol_traitbank",
      "name": "EOL TraitBank (via Zenodo)",
      "license": "Per record: CC0 / CC BY 4.0 / public domain only",
      "license_url": "https://doi.org/10.5281/zenodo.17315431",
      "attribution": "Encyclopedia of Life TraitBank, via Zenodo (DOI 10.5281/zenodo.17315431). Only commercially-safe per-record licences retained.",
      "url": "https://doi.org/10.5281/zenodo.17315431",
      "provides": "Leaf retention, life form, growth form and succulence (growth_traits dimension), safe per-record licences only."
    },
    {
      "key": "traits_mined",
      "name": "Traits mined from USDA NRCS plant guides",
      "license": "Public domain (source documents)",
      "license_url": "https://plants.usda.gov/",
      "attribution": "Traits extracted from USDA NRCS plant guides and fact sheets (plants.usda.gov, public domain). Assembled by BotanAI.",
      "url": "https://plants.usda.gov/",
      "provides": "Leaf type, phenology and other traits read from public-domain prose (growth_traits dimension); each value carries a verbatim source quote and is flagged extracted:true."
    },
    {
      "key": "inaturalist",
      "name": "iNaturalist open data",
      "license": "Per photograph: CC0, CC BY or CC BY-SA only",
      "license_url": "https://www.inaturalist.org/pages/help#cc",
      "attribution": "iNaturalist contributors. Each photograph carries its own licence and photographer credit.",
      "url": "https://github.com/inaturalist/inaturalist-open-data",
      "provides": "Photographs (per-image metadata on the per-species .json sibling) and the taxon id. No NonCommercial image is in this corpus."
    },
    {
      "key": "aiy",
      "name": "Google AIY plants V1 + BotanAI measured confusion",
      "license": "Apache 2.0 (model); BotanAI (measured confusion data)",
      "license_url": "https://www.apache.org/licenses/LICENSE-2.0",
      "attribution": "On-device identification model: Google AIY plants V1. Confusion measured by BotanAI over openly licensed photographs.",
      "url": "https://www.kaggle.com/models/google/aiy",
      "provides": "The identification block: whether the app identifies a species, and measured lookalikes."
    }
  ],
  "dumps": [
    {
      "id": "species",
      "file": "botanai-species.jsonl.gz",
      "path": "/data/botanai-species.jsonl.gz",
      "url": "https://botanai.app/data/botanai-species.jsonl.gz",
      "title": "Combined species corpus",
      "description": "One JSON object per line: the unified, provenance-tagged record for every documented species. Carries the stable id (slug + WFO id), nomenclature, native range, climate envelope, the identification block, and all seven provenance-tagged dimensions, each fact with its source and licence. Phenology is omitted (CC BY-NC upstream) and lives on the per-species .json; photographs are summarised with a pointer to the per-species .json for full per-image metadata.",
      "format": "application/gzip",
      "content_type": "application/x-ndjson",
      "records": 56125,
      "bytes": 41360129,
      "bytes_human": "39.4 MB",
      "sha256": "e32fc837b6af914ac43c1ad9df9f2e65ba0e1adccf5ecc1626c1fe3cd65661d2",
      "license": "CC BY 4.0 (record); underlying facts per their source, see sources[]",
      "license_url": "https://creativecommons.org/licenses/by/4.0/",
      "attribution": "BotanAI, https://botanai.app"
    },
    {
      "id": "uses",
      "file": "uses.jsonl.gz",
      "path": "/data/uses.jsonl.gz",
      "url": "https://botanai.app/data/uses.jsonl.gz",
      "title": "uses dimension",
      "description": "One JSON object per line for every species carrying this dimension, in the same shape the species pages and the .json sibling render. The FIRST line is a {\"_meta\": {...}} header carrying this dimension's source, licence and sync date.",
      "format": "application/gzip",
      "content_type": "application/x-ndjson",
      "records": 17078,
      "header_line": "_meta",
      "bytes": 354028,
      "bytes_human": "345.7 KB",
      "sha256": "22617de9fafaba182e9bf16009d3174bd9ce12bc31795c083746c51c5e5df481",
      "license": "CC-BY 4.0",
      "source": "Kew World Checklist of Useful Plant Species",
      "source_url": "https://doi.org/10.5063/F1CV4G34",
      "synced": "2026-07-18",
      "attribution": "Kew World Checklist of Useful Plant Species. Assembled by BotanAI, https://botanai.app"
    },
    {
      "id": "phytochemistry",
      "file": "phytochemistry.jsonl.gz",
      "path": "/data/phytochemistry.jsonl.gz",
      "url": "https://botanai.app/data/phytochemistry.jsonl.gz",
      "title": "phytochem dimension",
      "description": "One JSON object per line for every species carrying this dimension, in the same shape the species pages and the .json sibling render. The FIRST line is a {\"_meta\": {...}} header carrying this dimension's source, licence and sync date.",
      "format": "application/gzip",
      "content_type": "application/x-ndjson",
      "records": 1414,
      "header_line": "_meta",
      "bytes": 180982,
      "bytes_human": "176.7 KB",
      "sha256": "a477ce186a93678e2838e58f8f0d4e68f8007744e9c57352beff013467f62134",
      "license": "CC0",
      "source": "Dr. Duke's Phytochemical & Ethnobotanical Database",
      "source_url": "https://doi.org/10.15482/USDA.ADC/1239279",
      "synced": "2026-07-18",
      "attribution": "Dr. Duke's Phytochemical & Ethnobotanical Database. Assembled by BotanAI, https://botanai.app"
    },
    {
      "id": "conservation",
      "file": "conservation.jsonl.gz",
      "path": "/data/conservation.jsonl.gz",
      "url": "https://botanai.app/data/conservation.jsonl.gz",
      "title": "conservation dimension",
      "description": "One JSON object per line for every species carrying this dimension, in the same shape the species pages and the .json sibling render. The FIRST line is a {\"_meta\": {...}} header carrying this dimension's source, licence and sync date.",
      "format": "application/gzip",
      "content_type": "application/x-ndjson",
      "records": 9990,
      "header_line": "_meta",
      "bytes": 183379,
      "bytes_human": "179.1 KB",
      "sha256": "d35ed6fbf2561d12bc6e2846e30bfdf81ca241c5a97baf096cb6dfce16d38cf1",
      "license": "CC0 (Wikidata); IUCN category is a factual label",
      "source": "IUCN Red List category via Wikidata (P141)",
      "source_url": "https://www.wikidata.org",
      "synced": "2026-07-18",
      "attribution": "IUCN Red List category via Wikidata (P141). Assembled by BotanAI, https://botanai.app"
    },
    {
      "id": "vernacular_names",
      "file": "vernacular-names.jsonl.gz",
      "path": "/data/vernacular-names.jsonl.gz",
      "url": "https://botanai.app/data/vernacular-names.jsonl.gz",
      "title": "names dimension",
      "description": "One JSON object per line for every species carrying this dimension, in the same shape the species pages and the .json sibling render. The FIRST line is a {\"_meta\": {...}} header carrying this dimension's source, licence and sync date.",
      "format": "application/gzip",
      "content_type": "application/x-ndjson",
      "records": 43468,
      "header_line": "_meta",
      "bytes": 3485736,
      "bytes_human": "3.3 MB",
      "sha256": "78d1a6807ddc2a88796a291b3128074f61a5136427139ed56eb9b5c02fb3e388",
      "license": "CC0 / per-source",
      "source": "Wikidata (P1843, CC0) + GBIF vernacular names",
      "source_url": "https://www.wikidata.org",
      "synced": "2026-07-18",
      "attribution": "Wikidata (P1843, CC0) + GBIF vernacular names. Assembled by BotanAI, https://botanai.app"
    },
    {
      "id": "interactions",
      "file": "interactions.jsonl.gz",
      "path": "/data/interactions.jsonl.gz",
      "url": "https://botanai.app/data/interactions.jsonl.gz",
      "title": "interactions dimension",
      "description": "One JSON object per line for every species carrying this dimension, in the same shape the species pages and the .json sibling render. The FIRST line is a {\"_meta\": {...}} header carrying this dimension's source, licence and sync date.",
      "format": "application/gzip",
      "content_type": "application/x-ndjson",
      "records": 19886,
      "header_line": "_meta",
      "bytes": 1695646,
      "bytes_human": "1.6 MB",
      "sha256": "ab1187e637b783ed790084dd69cf312b6b1a954de4cadd2eb0e764fff9171c9e",
      "license": "CC-BY 4.0 (aggregate) / per-source",
      "source": "Global Biotic Interactions (GloBI)",
      "source_url": "https://www.globalbioticinteractions.org",
      "synced": "2026-07-18",
      "attribution": "Global Biotic Interactions (GloBI). Assembled by BotanAI, https://botanai.app"
    },
    {
      "id": "nomenclature",
      "file": "nomenclature.jsonl.gz",
      "path": "/data/nomenclature.jsonl.gz",
      "url": "https://botanai.app/data/nomenclature.jsonl.gz",
      "title": "nomenclature dimension",
      "description": "One JSON object per line for every species carrying this dimension, in the same shape the species pages and the .json sibling render. The FIRST line is a {\"_meta\": {...}} header carrying this dimension's source, licence and sync date.",
      "format": "application/gzip",
      "content_type": "application/x-ndjson",
      "records": 54385,
      "header_line": "_meta",
      "bytes": 2667700,
      "bytes_human": "2.5 MB",
      "sha256": "5263f0a261fcbbcad26a1a93e98aebfe868eeb58eb62bc4fa5c67d2f2eeb9d49",
      "license": "CC-BY 4.0",
      "source": "IPNI (International Plant Names Index)",
      "source_url": "https://www.ipni.org",
      "synced": "2026-07-18",
      "attribution": "IPNI (International Plant Names Index). Assembled by BotanAI, https://botanai.app"
    },
    {
      "id": "growth_traits",
      "file": "growth-traits.jsonl.gz",
      "path": "/data/growth-traits.jsonl.gz",
      "url": "https://botanai.app/data/growth-traits.jsonl.gz",
      "title": "growth-traits dimension",
      "description": "One JSON object per line for every species carrying this dimension, in the same shape the species pages and the .json sibling render. The FIRST line is a {\"_meta\": {...}} header carrying this dimension's source, licence and sync date.",
      "format": "application/gzip",
      "content_type": "application/x-ndjson",
      "records": 49475,
      "header_line": "_meta",
      "bytes": 2379579,
      "bytes_human": "2.3 MB",
      "sha256": "974f8e42e063c0b1de0ccf8c30ca46be172686c44c0ece25121aa09ceea9bc38",
      "license": "per source (public domain, CC BY 4.0, CC0)",
      "source": "USDA PLANTS, GIFT, Wikidata, EOL TraitBank (via Zenodo) and traits mined from USDA NRCS plant guides",
      "source_url": "https://botanai.app/sources/",
      "synced": "2026-07-19",
      "attribution": "USDA PLANTS, GIFT, Wikidata, EOL TraitBank (via Zenodo) and traits mined from USDA NRCS plant guides. Assembled by BotanAI, https://botanai.app"
    }
  ]
}