Using machine learning to alleviate the allometric effect in otolith shape-based species discrimination: the role of a triplet loss function
Abstract 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,Electr...
Published in: | ICES Journal of Marine Science |
---|---|
Main Authors: | , |
Other Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Oxford University Press (OUP)
2023
|
Subjects: | |
Online Access: | http://dx.doi.org/10.1093/icesjms/fsad052 https://academic.oup.com/icesjms/article-pdf/80/5/1277/50737213/fsad052.pdf |
id |
croxfordunivpr:10.1093/icesjms/fsad052 |
---|---|
record_format |
openpolar |
spelling |
croxfordunivpr:10.1093/icesjms/fsad052 2024-04-07T07:46:33+00:00 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 Whidden, Christopher Latin America of Chinese Scholarship Council National Science Foundation of China National Key Research and Development Program of China 2023 http://dx.doi.org/10.1093/icesjms/fsad052 https://academic.oup.com/icesjms/article-pdf/80/5/1277/50737213/fsad052.pdf en eng Oxford University Press (OUP) https://creativecommons.org/licenses/by/4.0/ ICES Journal of Marine Science volume 80, issue 5, page 1277-1290 ISSN 1054-3139 1095-9289 Ecology Aquatic Science Ecology, Evolution, Behavior and Systematics Oceanography journal-article 2023 croxfordunivpr https://doi.org/10.1093/icesjms/fsad052 2024-03-08T03:10:03Z Abstract 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* Southern Ocean Oxford University Press Southern Ocean ICES Journal of Marine Science |
institution |
Open Polar |
collection |
Oxford University Press |
op_collection_id |
croxfordunivpr |
language |
English |
topic |
Ecology Aquatic Science Ecology, Evolution, Behavior and Systematics Oceanography |
spellingShingle |
Ecology Aquatic Science Ecology, Evolution, Behavior and Systematics Oceanography 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 |
Ecology Aquatic Science Ecology, Evolution, Behavior and Systematics Oceanography |
description |
Abstract 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. |
author2 |
Whidden, Christopher Latin America of Chinese Scholarship Council National Science Foundation of China National Key Research and Development Program of China |
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 |
http://dx.doi.org/10.1093/icesjms/fsad052 https://academic.oup.com/icesjms/article-pdf/80/5/1277/50737213/fsad052.pdf |
geographic |
Southern Ocean |
geographic_facet |
Southern Ocean |
genre |
Antarc* Southern Ocean |
genre_facet |
Antarc* Southern Ocean |
op_source |
ICES Journal of Marine Science volume 80, issue 5, page 1277-1290 ISSN 1054-3139 1095-9289 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.1093/icesjms/fsad052 |
container_title |
ICES Journal of Marine Science |
_version_ |
1795666788571152384 |