Using machine learning to alleviate the allometric effect in otolith shape-based species discrimination: the role of a triplet loss function
Species identification by fish otoliths is an effective and appropriate approach. However, the allometric growth of otoliths can cause discrimination confusion, particularly in juvenile otolith classification. In the Southern Ocean, Chionodraco rastrospinosus,Krefftichthys anderssoni,Electrona carls...
Published in: | ICES Journal of Marine Science |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Oxford University Press (OUP)
2023
|
Subjects: | |
Online Access: | https://archimer.ifremer.fr/doc/00831/94306/101696.pdf https://archimer.ifremer.fr/doc/00831/94306/101697.docx https://doi.org/10.1093/icesjms/fsad052 https://archimer.ifremer.fr/doc/00831/94306/ |
id |
ftarchimer:oai:archimer.ifremer.fr:94306 |
---|---|
record_format |
openpolar |
spelling |
ftarchimer:oai:archimer.ifremer.fr:94306 2023-12-24T10:09:06+01:00 Using machine learning to alleviate the allometric effect in otolith shape-based species discrimination: the role of a triplet loss function Chen, Yuwen Zhu, Guoping 2023-06 application/pdf https://archimer.ifremer.fr/doc/00831/94306/101696.pdf https://archimer.ifremer.fr/doc/00831/94306/101697.docx https://doi.org/10.1093/icesjms/fsad052 https://archimer.ifremer.fr/doc/00831/94306/ eng eng Oxford University Press (OUP) https://archimer.ifremer.fr/doc/00831/94306/101696.pdf https://archimer.ifremer.fr/doc/00831/94306/101697.docx doi:10.1093/icesjms/fsad052 https://archimer.ifremer.fr/doc/00831/94306/ info:eu-repo/semantics/openAccess restricted use Ices Journal Of Marine Science (1054-3139) (Oxford University Press (OUP)), 2023-06 , Vol. 80 , N. 5 , P. 1277-1290 allometric effect antarctic neural network otolith shape wavelet transform text Article info:eu-repo/semantics/article 2023 ftarchimer https://doi.org/10.1093/icesjms/fsad052 2023-11-28T23:51:10Z Species identification by fish otoliths is an effective and appropriate approach. However, the allometric growth of otoliths can cause discrimination confusion, particularly in juvenile otolith classification. In the Southern Ocean, Chionodraco rastrospinosus,Krefftichthys anderssoni,Electrona carlsbergi, andPleuragramma antarcticum are frequently caught together in krill fishery as bycatch species. Furthermore, the otolith shape of these four species is relatively similar in juvenile fish, making the identification of fish species difficult. In this study, we tried and evaluated many commonly used machine learning techniques to solve this problem. Eventually, by introducing a triplet loss function (function used to reduce intraspecific variation and increase inter-specific variation), the discrimination confusion caused by the allometric growth of otoliths was reduced. The classification results show that the neural network model with the triplet loss function achieves the best classification accuracy of 96%. The proposed method can help improve otolith classification performance, especially under the context of limited sampling effort, which is of great importance for trophic ecology and the study of fish life history. Article in Journal/Newspaper Antarc* Antarctic Southern Ocean Archimer (Archive Institutionnelle de l'Ifremer - Institut français de recherche pour l'exploitation de la mer) Antarctic Southern Ocean ICES Journal of Marine Science |
institution |
Open Polar |
collection |
Archimer (Archive Institutionnelle de l'Ifremer - Institut français de recherche pour l'exploitation de la mer) |
op_collection_id |
ftarchimer |
language |
English |
topic |
allometric effect antarctic neural network otolith shape wavelet transform |
spellingShingle |
allometric effect antarctic neural network otolith shape wavelet transform Chen, Yuwen Zhu, Guoping Using machine learning to alleviate the allometric effect in otolith shape-based species discrimination: the role of a triplet loss function |
topic_facet |
allometric effect antarctic neural network otolith shape wavelet transform |
description |
Species identification by fish otoliths is an effective and appropriate approach. However, the allometric growth of otoliths can cause discrimination confusion, particularly in juvenile otolith classification. In the Southern Ocean, Chionodraco rastrospinosus,Krefftichthys anderssoni,Electrona carlsbergi, andPleuragramma antarcticum are frequently caught together in krill fishery as bycatch species. Furthermore, the otolith shape of these four species is relatively similar in juvenile fish, making the identification of fish species difficult. In this study, we tried and evaluated many commonly used machine learning techniques to solve this problem. Eventually, by introducing a triplet loss function (function used to reduce intraspecific variation and increase inter-specific variation), the discrimination confusion caused by the allometric growth of otoliths was reduced. The classification results show that the neural network model with the triplet loss function achieves the best classification accuracy of 96%. The proposed method can help improve otolith classification performance, especially under the context of limited sampling effort, which is of great importance for trophic ecology and the study of fish life history. |
format |
Article in Journal/Newspaper |
author |
Chen, Yuwen Zhu, Guoping |
author_facet |
Chen, Yuwen Zhu, Guoping |
author_sort |
Chen, Yuwen |
title |
Using machine learning to alleviate the allometric effect in otolith shape-based species discrimination: the role of a triplet loss function |
title_short |
Using machine learning to alleviate the allometric effect in otolith shape-based species discrimination: the role of a triplet loss function |
title_full |
Using machine learning to alleviate the allometric effect in otolith shape-based species discrimination: the role of a triplet loss function |
title_fullStr |
Using machine learning to alleviate the allometric effect in otolith shape-based species discrimination: the role of a triplet loss function |
title_full_unstemmed |
Using machine learning to alleviate the allometric effect in otolith shape-based species discrimination: the role of a triplet loss function |
title_sort |
using machine learning to alleviate the allometric effect in otolith shape-based species discrimination: the role of a triplet loss function |
publisher |
Oxford University Press (OUP) |
publishDate |
2023 |
url |
https://archimer.ifremer.fr/doc/00831/94306/101696.pdf https://archimer.ifremer.fr/doc/00831/94306/101697.docx https://doi.org/10.1093/icesjms/fsad052 https://archimer.ifremer.fr/doc/00831/94306/ |
geographic |
Antarctic Southern Ocean |
geographic_facet |
Antarctic Southern Ocean |
genre |
Antarc* Antarctic Southern Ocean |
genre_facet |
Antarc* Antarctic Southern Ocean |
op_source |
Ices Journal Of Marine Science (1054-3139) (Oxford University Press (OUP)), 2023-06 , Vol. 80 , N. 5 , P. 1277-1290 |
op_relation |
https://archimer.ifremer.fr/doc/00831/94306/101696.pdf https://archimer.ifremer.fr/doc/00831/94306/101697.docx doi:10.1093/icesjms/fsad052 https://archimer.ifremer.fr/doc/00831/94306/ |
op_rights |
info:eu-repo/semantics/openAccess restricted use |
op_doi |
https://doi.org/10.1093/icesjms/fsad052 |
container_title |
ICES Journal of Marine Science |
_version_ |
1786205857209384960 |