{ "name": "bionomia-attributions", "id": "f1ddda5a-ac85-46a3-955c-b75277c6a600", "licenses": [ { "name": "cc-by-4.0", "path": "http://creativecommons.org/licenses/by/4.0/legalcode" } ], "profile": "tabular-data-package", "title": "ATTRIBUTIONS MADE FOR: Life beneath the ice: jellyfish and ctenophores from the Ross Sea, Antarctica, with an image-based training set for machine learning", "description": "Southern Ocean ecosystems are currently experiencing increased environmental changes and anthropogenic pressures, urging scientists to report on their biodiversity and biogeography. One major marine taxonomically diverse and trophically important group that has, however, stayed largely understudied until now is the gelatinous zooplankton, including cnidarians, ctenophores and tunicates. This data scarcity is predominantly due to many of these fragile, soft-bodied organisms being easily fragmented and/or destroyed with traditional net sampling methods. Progress in alternative survey methods including, for instance, optics-based methods is slowly starting to overcome these obstacles. As video annotation by human observers is both time-consuming and financially costly, machine learning techniques should be developed for the analysis of in-situ image-based datasets. This requires taxonomically accurate training sets for correct species identification and the present paper is the first to provide such data.In this study, we twice conducted three week-long in situ optics-based surveys of gelatinous zooplankton found under the ice in the McMurdo Sound, Antarctica. Our study constitutes the first optics-based survey of gelatinous zooplankton in the Ross Sea and the first study to use in situ observations to describe taxonomic, trophic, and behavioral characteristics of gelatinous zooplankton from the Southern Ocean. Despite the small geographic and temporal scales of our study, we provided new undescribed morphological traits for all observed gelatinous zooplankton species (eight cnidarian and four ctenophore species). Three ctenophores and one leptomedusa likely represent undescribed species. Furthermore, along with the photography and videography, we prepared a Common Objects in Context (COCO) dataset, so that this study is the first to provide a taxonomist-ratified image training set for future machine learning algorithm development concerning Southern Ocean gelatinous zooplankton species.", "datasetKey": "f1ddda5a-ac85-46a3-955c-b75277c6a600", "doi": "https://doi.org/10.5281/zenodo.10506516", "homepage": "https://bionomia.net/dataset/f1ddda5a-ac85-46a3-955c-b75277c6a600", "created": "2024-06-30T22:11:06+00:00", "sources": [ { "title": "Life beneath the ice: jellyfish and ctenophores from the Ross Sea, Antarctica, with an image-based training set for machine learning", "path": "https://doi.org/10.3897/bdj.9.e69374" } ], "keywords": [ "specimen", "museum", "collection", "credit", "attribution", "bionomia" ], "image": "https://bionomia.net/images/logo.png", "resources": [ { "name": "users", "description": "List of unique people that have either claimed or been attributed occurrence records through examination of either dwc:recordedBy or dwc:identifiedBy. Wikidata-based people contain some demographic information.", "format": "csv", "mediatype": "text/csv", "encoding": "utf-8", "profile": "tabular-data-resource", "schema": { "fields": [ { "name": "id", "type": "integer" }, { "name": "name", "type": "string", "skos:exactMatch": "http://schema.org/name" }, { "name": "familyName", "type": "string", "skos:exactMatch": "http://schema.org/familyName" }, { "name": "particle", "type": "string" }, { "name": "givenName", "type": "string", "skos:exactMatch": "http://schema.org/givenName" }, { "name": "alternateName", "type": "array", "skos:exactMatch": "http://schema.org/alternateName" }, { "name": "sameAs", "type": "string", "format": "uri", "skos:exactMatch": "http://schema.org/sameAs" }, { "name": "orcid", "type": "string" }, { "name": "wikidata", "type": "string" }, { "name": "birthDate", "type": "date", "skos:exactMatch": "https://schema.org/birthDate" }, { "name": "birthDatePrecision", "type": "string", "description": "Values are year, month, or day and indicate the precision of birthDate; portions of birthDate should be ignored below that of the birthDatePrecision." }, { "name": "deathDate", "type": "date", "skos:exactMatch": "https://schema.org/deathDate" }, { "name": "deathDatePrecision", "type": "string", "description": "Values are year, month, or day and indicate the precision of deathDate; portions of deathDate should be ignored below that of the deathDatePrecision." } ] }, "primaryKey": "id", "path": "https://bionomia.net/dataset/f1ddda5a-ac85-46a3-955c-b75277c6a600/users.csv.zip", "compression": "zip", "bytes": 268, "hash": "a012f3a765ba696862d22b5d1643394c" }, { "name": "problem-determiner-dates", "description": "Associated occurrence records whose dateIdentified are earlier than a determiner's birthDate or later than their deathDate.", "format": "csv", "mediatype": "text/csv", "encoding": "utf-8", "profile": "tabular-data-resource", "schema": { "fields": [ { "name": "occurrence_id", "type": "integer" }, { "name": "catalogNumber", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/catalogNumber" }, { "name": "user_id", "type": "integer" }, { "name": "wikidata", "type": "string" }, { "name": "birthDate", "type": "date", "skos:exactMatch": "https://schema.org/birthDate" }, { "name": "birthDatePrecision", "type": "string", "description": "Values are year, month, or day and indicate the precision of birthDate; portions of birthDate should be ignored below that of the birthDatePrecision." }, { "name": "deathDate", "type": "date", "skos:exactMatch": "https://schema.org/deathDate" }, { "name": "deathDatePrecision", "type": "string", "description": "Values are year, month, or day and indicate the precision of deathDate; portions of deathDate should be ignored below that of the deathDatePrecision." }, { "name": "dateIdentified", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/dateIdentified" } ] }, "foreignKeys": [ { "fields": "user_id", "reference": { "resource": "users", "fields": "id" } }, { "fields": "occurrence_id", "reference": { "resource": "occurrences", "fields": "gbifID" } } ], "path": "https://bionomia.net/dataset/f1ddda5a-ac85-46a3-955c-b75277c6a600/problem_determiner_dates.csv.zip", "compression": "zip", "bytes": 237, "hash": "8f8efedd50467b9a5f35036be2d04b4a" }, { "name": "problem-collector-dates", "description": "Associated occurrence records whose eventDates are earlier than a collector's birthDate or later than their deathDate.", "format": "csv", "mediatype": "text/csv", "encoding": "utf-8", "profile": "tabular-data-resource", "schema": { "fields": [ { "name": "occurrence_id", "type": "integer" }, { "name": "catalogNumber", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/catalogNumber" }, { "name": "user_id", "type": "integer" }, { "name": "wikidata", "type": "string" }, { "name": "birthDate", "type": "date", "skos:exactMatch": "https://schema.org/birthDate" }, { "name": "birthDatePrecision", "type": "string", "description": "Values are year, month, or day and indicate the precision of birthDate; portions of birthDate should be ignored below that of the birthDatePrecision." }, { "name": "deathDate", "type": "date", "skos:exactMatch": "https://schema.org/deathDate" }, { "name": "deathDatePrecision", "type": "string", "description": "Values are year, month, or day and indicate the precision of deathDate; portions of deathDate should be ignored below that of the deathDatePrecision." }, { "name": "eventDate", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/eventDate" }, { "name": "year", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/year" } ] }, "foreignKeys": [ { "fields": "user_id", "reference": { "resource": "users", "fields": "id" } }, { "fields": "occurrence_id", "reference": { "resource": "occurrences", "fields": "gbifID" } } ], "path": "https://bionomia.net/dataset/f1ddda5a-ac85-46a3-955c-b75277c6a600/problem_collector_dates.csv.zip", "compression": "zip", "bytes": 233, "hash": "71cfba3ff7f3e12bb1691350dd48a34f" }, { "name": "occurrences", "description": "Occurrence records shared to GBIF, limited to those linked to a collector or determiner.", "format": "csv", "mediatype": "text/csv", "encoding": "utf-8", "profile": "tabular-data-resource", "schema": { "fields": [ { "name": "gbifID", "type": "integer" }, { "name": "datasetKey", "type": "string", "format": "uuid", "skos:exactMatch": "http://rs.gbif.org/terms/1.0/datasetKey" }, { "name": "license", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/license" }, { "name": "occurrenceID", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/occurrenceID" }, { "name": "basisOfRecord", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/basisOfRecord" }, { "name": "dateIdentified", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/dateIdentified" }, { "name": "decimalLatitude", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/decimalLatitude" }, { "name": "decimalLongitude", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/decimalLongitude" }, { "name": "country", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/country" }, { "name": "countryCode", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/countryCode" }, { "name": "eventDate", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/eventDate" }, { "name": "year", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/year" }, { "name": "kingdom", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/kingdom" }, { "name": "family", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/family" }, { "name": "identifiedBy", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/identifiedBy" }, { "name": "institutionCode", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/institutionCode" }, { "name": "collectionCode", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/collectionCode" }, { "name": "catalogNumber", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/catalogNumber" }, { "name": "recordedBy", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/recordedBy" }, { "name": "scientificName", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/scientificName" }, { "name": "typeStatus", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/typeStatus" }, { "name": "recordedByID", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/recordedByID" }, { "name": "identifiedByID", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/identifiedByID" } ] }, "primaryKey": "gbifID", "path": "https://bionomia.net/dataset/f1ddda5a-ac85-46a3-955c-b75277c6a600/occurrences.csv.zip", "compression": "zip", "bytes": 939, "hash": "e39244192e7fc3d18b2fedbc1144048b" }, { "name": "unascribed", "description": "Negative assertions made alongside the provenance, which may help inform local disambiguation activities.", "format": "csv", "mediatype": "text/csv", "encoding": "utf-8", "profile": "tabular-data-resource", "schema": { "fields": [ { "name": "occurrence_id", "type": "integer" }, { "name": "catalogNumber", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/catalogNumber" }, { "name": "recordedBy", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/recordedeBy" }, { "name": "recordedByID", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/recordedByID" }, { "name": "identifiedBy", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/identifiedBy" }, { "name": "identifiedByID", "type": "string", "skos:exactMatch": "http://rs.tdwg.org/dwc/terms/identifiedByID" }, { "name": "differentFrom", "type": "string", "skos:exactMatch": "http://www.w3.org/2002/07/owl#differentFrom" }, { "name": "user_id", "type": "integer" }, { "name": "name", "type": "string", "skos:exactMatch": "http://schema.org/name" }, { "name": "wikidata", "type": "string" }, { "name": "orcid", "type": "string" }, { "name": "createdBy", "type": "string", "skos:exactMatch": "http://schema.org/name" }, { "name": "createdByURI", "type": "string", "format": "uri" }, { "name": "createdDateTime", "type": "datetime", "format": "any" }, { "name": "modifiedDateTime", "type": "datetime", "format": "any" } ] }, "foreignKeys": [ { "fields": "occurrence_id", "reference": { "resource": "occurrences", "fields": "gbifID" } }, { "fields": "user_id", "reference": { "resource": "users", "fields": "id" } } ], "path": "https://bionomia.net/dataset/f1ddda5a-ac85-46a3-955c-b75277c6a600/not_them_assertions.csv.zip", "compression": "zip", "bytes": 259, "hash": "cdfa69da865a4ede8b11d10a02bc8576" }, { "name": "article-occurrences", "description": "A join table between occurrence and article to permit examination of particular occurrence records that were included in a GBIF download and later used in a published article.", "format": "csv", "mediatype": "text/csv", "encoding": "utf-8", "profile": "tabular-data-resource", "schema": { "fields": [ { "name": "article_id", "type": "integer" }, { "name": "occurrence_id", "type": "integer" } ] }, "foreignKeys": [ { "fields": "article_id", "reference": { "resource": "articles", "fields": "id" } }, { "fields": "occurrence_id", "reference": { "resource": "occurrences", "fields": "gbifID" } } ], "path": "https://bionomia.net/dataset/f1ddda5a-ac85-46a3-955c-b75277c6a600/citations.csv.zip", "compression": "zip", "bytes": 148, "hash": "2af61d2d32ffade1b5cbe271a7a15bb2" }, { "name": "attributions", "description": "Details about the provenance for an attributed or claimed occurrence record.", "format": "csv", "mediatype": "text/csv", "encoding": "utf-8", "profile": "tabular-data-resource", "schema": { "fields": [ { "name": "user_id", "type": "integer" }, { "name": "occurrence_id", "type": "integer" }, { "name": "identifiedBy", "type": "string", "format": "uri", "skos:exactMatch": "http://rs.tdwg.org/dwc/iri/identifiedBy" }, { "name": "recordedBy", "type": "string", "format": "uri", "skos:exactMatch": "http://rs.tdwg.org/dwc/iri/recordedBy" }, { "name": "createdBy", "type": "string", "skos:exactMatch": "http://schema.org/name" }, { "name": "createdByURI", "type": "string", "format": "uri" }, { "name": "createdDateTime", "type": "datetime", "format": "any" }, { "name": "modifiedDateTime", "type": "datetime", "format": "any" } ] }, "foreignKeys": [ { "fields": "user_id", "reference": { "resource": "users", "fields": "id" } }, { "fields": "occurrence_id", "reference": { "resource": "occurrences", "fields": "gbifID" } } ], "path": "https://bionomia.net/dataset/f1ddda5a-ac85-46a3-955c-b75277c6a600/attributions.csv.zip", "compression": "zip", "bytes": 422, "hash": "99086466ab3480af134e2a775bb37c62" }, { "name": "articles", "description": "Published articles whose authors had downloaded and referenced a data package from GBIF containing occurrences that are linked to collectors or determiners.", "format": "csv", "mediatype": "text/csv", "encoding": "utf-8", "profile": "tabular-data-resource", "schema": { "fields": [ { "name": "id", "type": "integer" }, { "name": "reference", "type": "string", "skos:exactMatch": "http://schema.org/name" }, { "name": "sameAs", "type": "string", "format": "uri", "skos:exactMatch": "http://schema.org/sameAs" }, { "name": "datasets", "type": "array", "format": "uri", "skos:exactMatch": "http://schema.org/sameAs" } ] }, "primaryKey": "id", "path": "https://bionomia.net/dataset/f1ddda5a-ac85-46a3-955c-b75277c6a600/articles.csv.zip", "compression": "zip", "bytes": 153, "hash": "adaab97e6738381c3f719093b9809967" } ] }