Acoustic Classification of Juvenile Pacific Salmon (Oncorhynchus spp) and Pacific Herring (Clupea pallasii) Schools Using Random Forests
Acoustic surveys are the standard approach for evaluating many fish stocks around the world. The analysis of such survey data requires the accurate echo-classification of target species. This classification is often challenging as many organisms exhibit overlapping characteristics in terms of shape,...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-07-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2022.857645/full |
| _version_ | 1818156583384776704 |
|---|---|
| author | Shani Rousseau Stéphane Gauthier Stéphane Gauthier Chrys Neville Stewart Johnson Marc Trudel |
| author_facet | Shani Rousseau Stéphane Gauthier Stéphane Gauthier Chrys Neville Stewart Johnson Marc Trudel |
| author_sort | Shani Rousseau |
| collection | DOAJ |
| description | Acoustic surveys are the standard approach for evaluating many fish stocks around the world. The analysis of such survey data requires the accurate echo-classification of target species. This classification is often challenging as many organisms exhibit overlapping characteristics in terms of shape, acoustic amplitude, and behavior. In this study, a random forest approach was used to distinguish juvenile Pacific salmon (Oncorhynchus spp) from Pacific herring (Clupea pallasii) aggregations using the acoustic and morphological characteristics of their echo traces. The acoustic data was collected with an autonomous, multi-frequency echosounder deployed on the seafloor in the Discovery Islands, British Columbia from May to September 2015. The model was able to differentiate juvenile Pacific salmon from Pacific herring with a 98% accuracy. School depth and school mean volume backscattering strength were the most important predictors in determining the school classification. This study supports other publications suggesting that random forests represent a promising approach to acoustic target classification in fisheries science. |
| first_indexed | 2024-12-11T15:00:36Z |
| format | Article |
| id | doaj.art-b040f3d8f1184e65aa44ea2570d58455 |
| institution | Directory Open Access Journal |
| issn | 2296-7745 |
| language | English |
| last_indexed | 2024-12-11T15:00:36Z |
| publishDate | 2022-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj.art-b040f3d8f1184e65aa44ea2570d584552022-12-22T01:01:11ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452022-07-01910.3389/fmars.2022.857645857645Acoustic Classification of Juvenile Pacific Salmon (Oncorhynchus spp) and Pacific Herring (Clupea pallasii) Schools Using Random ForestsShani Rousseau0Stéphane Gauthier1Stéphane Gauthier2Chrys Neville3Stewart Johnson4Marc Trudel5Maurice Lamontagne Institute, Fisheries and Oceans Canada, Mont-Joli, QC, CanadaInstitute of Ocean Sciences, Fisheries and Oceans Canada, Sidney, BC, CanadaDepartment of Biology, University of Victoria, Victoria, BC, CanadaPacific Biological Station, Fisheries and Oceans Canada, Nanaimo, BC, CanadaPacific Biological Station, Fisheries and Oceans Canada, Nanaimo, BC, CanadaSt. Andrews Biological Station, Fisheries and Oceans Canada, St. Andrews, NB, CanadaAcoustic surveys are the standard approach for evaluating many fish stocks around the world. The analysis of such survey data requires the accurate echo-classification of target species. This classification is often challenging as many organisms exhibit overlapping characteristics in terms of shape, acoustic amplitude, and behavior. In this study, a random forest approach was used to distinguish juvenile Pacific salmon (Oncorhynchus spp) from Pacific herring (Clupea pallasii) aggregations using the acoustic and morphological characteristics of their echo traces. The acoustic data was collected with an autonomous, multi-frequency echosounder deployed on the seafloor in the Discovery Islands, British Columbia from May to September 2015. The model was able to differentiate juvenile Pacific salmon from Pacific herring with a 98% accuracy. School depth and school mean volume backscattering strength were the most important predictors in determining the school classification. This study supports other publications suggesting that random forests represent a promising approach to acoustic target classification in fisheries science.https://www.frontiersin.org/articles/10.3389/fmars.2022.857645/fullrandom forestmachine learningacoustic classificationsalmonherring |
| spellingShingle | Shani Rousseau Stéphane Gauthier Stéphane Gauthier Chrys Neville Stewart Johnson Marc Trudel Acoustic Classification of Juvenile Pacific Salmon (Oncorhynchus spp) and Pacific Herring (Clupea pallasii) Schools Using Random Forests Frontiers in Marine Science random forest machine learning acoustic classification salmon herring |
| title | Acoustic Classification of Juvenile Pacific Salmon (Oncorhynchus spp) and Pacific Herring (Clupea pallasii) Schools Using Random Forests |
| title_full | Acoustic Classification of Juvenile Pacific Salmon (Oncorhynchus spp) and Pacific Herring (Clupea pallasii) Schools Using Random Forests |
| title_fullStr | Acoustic Classification of Juvenile Pacific Salmon (Oncorhynchus spp) and Pacific Herring (Clupea pallasii) Schools Using Random Forests |
| title_full_unstemmed | Acoustic Classification of Juvenile Pacific Salmon (Oncorhynchus spp) and Pacific Herring (Clupea pallasii) Schools Using Random Forests |
| title_short | Acoustic Classification of Juvenile Pacific Salmon (Oncorhynchus spp) and Pacific Herring (Clupea pallasii) Schools Using Random Forests |
| title_sort | acoustic classification of juvenile pacific salmon oncorhynchus spp and pacific herring clupea pallasii schools using random forests |
| topic | random forest machine learning acoustic classification salmon herring |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2022.857645/full |
| work_keys_str_mv | AT shanirousseau acousticclassificationofjuvenilepacificsalmononcorhynchussppandpacificherringclupeapallasiischoolsusingrandomforests AT stephanegauthier acousticclassificationofjuvenilepacificsalmononcorhynchussppandpacificherringclupeapallasiischoolsusingrandomforests AT stephanegauthier acousticclassificationofjuvenilepacificsalmononcorhynchussppandpacificherringclupeapallasiischoolsusingrandomforests AT chrysneville acousticclassificationofjuvenilepacificsalmononcorhynchussppandpacificherringclupeapallasiischoolsusingrandomforests AT stewartjohnson acousticclassificationofjuvenilepacificsalmononcorhynchussppandpacificherringclupeapallasiischoolsusingrandomforests AT marctrudel acousticclassificationofjuvenilepacificsalmononcorhynchussppandpacificherringclupeapallasiischoolsusingrandomforests |