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: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
Pensoft Publishers
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3897/BDJ.9.e69374 |
id |
ftzenodo:oai:zenodo.org:5241351 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
Zenodo |
op_collection_id |
ftzenodo |
language |
unknown |
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 |
Article in Journal/Newspaper |
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 |
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, (2021-08-16) |
op_relation |
https://doi.org/10.3897/BDJ.9.e69374.figure3 https://doi.org/10.3897/BDJ.9.e69374.figure11b https://doi.org/10.3897/BDJ.9.e69374.figure11d https://doi.org/10.3897/BDJ.9.e69374.figure7 https://doi.org/10.3897/BDJ.9.e69374.figure11c https://doi.org/10.3897/BDJ.9.e69374.figure1 https://doi.org/10.3897/BDJ.9.e69374.figure20 https://doi.org/10.3897/BDJ.9.e69374.figure10d https://doi.org/10.3897/BDJ.9.e69374.figure11f https://doi.org/10.3897/BDJ.9.e69374.figure14 https://doi.org/10.3897/BDJ.9.e69374.figure15 https://doi.org/10.3897/BDJ.9.e69374.figure8 https://doi.org/10.3897/BDJ.9.e69374.figure6 https://doi.org/10.3897/BDJ.9.e69374.figure10b https://doi.org/10.3897/BDJ.9.e69374.figure12 https://doi.org/10.3897/BDJ.9.e69374.figure19 https://doi.org/10.3897/BDJ.9.e69374.figure2 https://doi.org/10.3897/BDJ.9.e69374.figure11a https://doi.org/10.3897/BDJ.9.e69374.figure13 https://doi.org/10.3897/BDJ.9.e69374.figure16 https://doi.org/10.3897/BDJ.9.e69374.figure5 https://doi.org/10.3897/BDJ.9.e69374.figure9 https://doi.org/10.3897/BDJ.9.e69374.figure10c https://doi.org/10.3897/BDJ.9.e69374.figure17 https://doi.org/10.3897/BDJ.9.e69374.figure11e https://doi.org/10.3897/BDJ.9.e69374.figure10a https://doi.org/10.3897/BDJ.9.e69374.figure18 https://doi.org/10.3897/BDJ.9.e69374.figure4 https://doi.org/10.3897/BDJ.9.e69374.suppl1 https://doi.org/10.3897/BDJ.9.e69374.suppl2 https://zenodo.org/communities/biosyslit https://doi.org/10.3897/BDJ.9.e69374 oai:zenodo.org:5241351 |
op_rights |
info:eu-repo/semantics/openAccess Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode |
op_doi |
https://doi.org/10.3897/BDJ.9.e6937410.3897/BDJ.9.e69374.figure310.3897/BDJ.9.e69374.figure11b10.3897/BDJ.9.e69374.figure11d10.3897/BDJ.9.e69374.figure710.3897/BDJ.9.e69374.figure11c10.3897/BDJ.9.e69374.figure110.3897/BDJ.9.e69374.figure2010.3897/BDJ.9.e6 |
container_title |
Biodiversity Data Journal |
container_volume |
9 |
_version_ |
1810486731212849152 |
spelling |
ftzenodo:oai:zenodo.org:5241351 2024-09-15T17:40:42+00:00 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 2021-08-16 https://doi.org/10.3897/BDJ.9.e69374 unknown Pensoft Publishers https://doi.org/10.3897/BDJ.9.e69374.figure3 https://doi.org/10.3897/BDJ.9.e69374.figure11b https://doi.org/10.3897/BDJ.9.e69374.figure11d https://doi.org/10.3897/BDJ.9.e69374.figure7 https://doi.org/10.3897/BDJ.9.e69374.figure11c https://doi.org/10.3897/BDJ.9.e69374.figure1 https://doi.org/10.3897/BDJ.9.e69374.figure20 https://doi.org/10.3897/BDJ.9.e69374.figure10d https://doi.org/10.3897/BDJ.9.e69374.figure11f https://doi.org/10.3897/BDJ.9.e69374.figure14 https://doi.org/10.3897/BDJ.9.e69374.figure15 https://doi.org/10.3897/BDJ.9.e69374.figure8 https://doi.org/10.3897/BDJ.9.e69374.figure6 https://doi.org/10.3897/BDJ.9.e69374.figure10b https://doi.org/10.3897/BDJ.9.e69374.figure12 https://doi.org/10.3897/BDJ.9.e69374.figure19 https://doi.org/10.3897/BDJ.9.e69374.figure2 https://doi.org/10.3897/BDJ.9.e69374.figure11a https://doi.org/10.3897/BDJ.9.e69374.figure13 https://doi.org/10.3897/BDJ.9.e69374.figure16 https://doi.org/10.3897/BDJ.9.e69374.figure5 https://doi.org/10.3897/BDJ.9.e69374.figure9 https://doi.org/10.3897/BDJ.9.e69374.figure10c https://doi.org/10.3897/BDJ.9.e69374.figure17 https://doi.org/10.3897/BDJ.9.e69374.figure11e https://doi.org/10.3897/BDJ.9.e69374.figure10a https://doi.org/10.3897/BDJ.9.e69374.figure18 https://doi.org/10.3897/BDJ.9.e69374.figure4 https://doi.org/10.3897/BDJ.9.e69374.suppl1 https://doi.org/10.3897/BDJ.9.e69374.suppl2 https://zenodo.org/communities/biosyslit https://doi.org/10.3897/BDJ.9.e69374 oai:zenodo.org:5241351 info:eu-repo/semantics/openAccess Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode Biodiversity Data Journal, 9, e69374, (2021-08-16) Southern Ocean gelatinous zooplankton siphonophore video annotation remotely-operated vehicle (ROV) Common Objects in Context (COCO) machine learning info:eu-repo/semantics/article 2021 ftzenodo https://doi.org/10.3897/BDJ.9.e6937410.3897/BDJ.9.e69374.figure310.3897/BDJ.9.e69374.figure11b10.3897/BDJ.9.e69374.figure11d10.3897/BDJ.9.e69374.figure710.3897/BDJ.9.e69374.figure11c10.3897/BDJ.9.e69374.figure110.3897/BDJ.9.e69374.figure2010.3897/BDJ.9.e6 2024-07-25T09:41:43Z 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. Article in Journal/Newspaper Antarc* Antarctica McMurdo Sound Ross Sea Southern Ocean Zenodo Biodiversity Data Journal 9 |