Life beneath the ice: jellyfish and ctenophores from the Ross Sea, Antarctica, with an image-based training set for machine learning
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...
Published in: | Biodiversity Data Journal |
---|---|
Main Authors: | , , |
Format: | Other/Unknown Material |
Language: | English |
Published: |
Pensoft Publishers
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3897/BDJ.9.e69374 https://bdj.pensoft.net/article/69374/ |
id |
ftpensoft:10.3897/BDJ.9.e69374 |
---|---|
record_format |
openpolar |
spelling |
ftpensoft:10.3897/BDJ.9.e69374 2023-05-15T14:05:14+02:00 Life beneath the ice: jellyfish and ctenophores from the Ross Sea, Antarctica, with an image-based training set for machine learning Verhaegen,Gerlien Cimoli,Emiliano Lindsay,Dhugal 2021 text/html https://doi.org/10.3897/BDJ.9.e69374 https://bdj.pensoft.net/article/69374/ en eng Pensoft Publishers info:eu-repo/semantics/altIdentifier/eissn/1314-2828 info:eu-repo/semantics/altIdentifier/pissn/1314-2836 info:eu-repo/semantics/openAccess Biodiversity Data Journal 9: e69374 Southern Ocean gelatinous zooplankton siphonophore video annotation remotely-operated vehicle (ROV) Common Objects in Context (COCO) machine learning Taxonomic Paper 2021 ftpensoft https://doi.org/10.3897/BDJ.9.e69374 2022-03-01T12:48:19Z 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. Other/Unknown Material Antarc* Antarctica McMurdo Sound Ross Sea Southern Ocean Pensoft Publishers McMurdo Sound Ross Sea Southern Ocean Biodiversity Data Journal 9 |
institution |
Open Polar |
collection |
Pensoft Publishers |
op_collection_id |
ftpensoft |
language |
English |
topic |
Southern Ocean gelatinous zooplankton siphonophore video annotation remotely-operated vehicle (ROV) Common Objects in Context (COCO) machine learning |
spellingShingle |
Southern Ocean gelatinous zooplankton siphonophore video annotation remotely-operated vehicle (ROV) Common Objects in Context (COCO) machine learning Verhaegen,Gerlien Cimoli,Emiliano Lindsay,Dhugal Life beneath the ice: jellyfish and ctenophores from the Ross Sea, Antarctica, with an image-based training set for machine learning |
topic_facet |
Southern Ocean gelatinous zooplankton siphonophore video annotation remotely-operated vehicle (ROV) Common Objects in Context (COCO) 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. |
format |
Other/Unknown Material |
author |
Verhaegen,Gerlien Cimoli,Emiliano Lindsay,Dhugal |
author_facet |
Verhaegen,Gerlien Cimoli,Emiliano Lindsay,Dhugal |
author_sort |
Verhaegen,Gerlien |
title |
Life beneath the ice: jellyfish and ctenophores from the Ross Sea, Antarctica, with an image-based training set for machine learning |
title_short |
Life beneath the ice: jellyfish and ctenophores from the Ross Sea, Antarctica, with an image-based training set for machine learning |
title_full |
Life beneath the ice: jellyfish and ctenophores from the Ross Sea, Antarctica, with an image-based training set for machine learning |
title_fullStr |
Life beneath the ice: jellyfish and ctenophores from the Ross Sea, Antarctica, with an image-based training set for machine learning |
title_full_unstemmed |
Life beneath the ice: jellyfish and ctenophores from the Ross Sea, Antarctica, with an image-based training set for machine learning |
title_sort |
life beneath the ice: jellyfish and ctenophores from the ross sea, antarctica, with an image-based training set for machine learning |
publisher |
Pensoft Publishers |
publishDate |
2021 |
url |
https://doi.org/10.3897/BDJ.9.e69374 https://bdj.pensoft.net/article/69374/ |
geographic |
McMurdo Sound Ross Sea Southern Ocean |
geographic_facet |
McMurdo Sound Ross Sea Southern Ocean |
genre |
Antarc* Antarctica McMurdo Sound Ross Sea Southern Ocean |
genre_facet |
Antarc* Antarctica McMurdo Sound Ross Sea Southern Ocean |
op_source |
Biodiversity Data Journal 9: e69374 |
op_relation |
info:eu-repo/semantics/altIdentifier/eissn/1314-2828 info:eu-repo/semantics/altIdentifier/pissn/1314-2836 |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.3897/BDJ.9.e69374 |
container_title |
Biodiversity Data Journal |
container_volume |
9 |
_version_ |
1766276976888250368 |