Model-informed classification of broadband acoustic backscatter from zooplankton in an in situ mesocosm
Classification of zooplankton to species with broadband echosounder data could increase the taxonomic resolution of acoustic surveys and reduce the dependence on net and trawl samples for ‘ground truthing’. Supervised classification with broadband echosounder data is limited by the acquisition of va...
Published in: | ICES Journal of Marine Science |
---|---|
Main Authors: | , , , , , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/11250/3106811 https://doi.org/10.1093/icesjms/fsad192 |
id |
ftimr:oai:imr.brage.unit.no:11250/3106811 |
---|---|
record_format |
openpolar |
spelling |
ftimr:oai:imr.brage.unit.no:11250/3106811 2024-01-07T09:41:28+01:00 Model-informed classification of broadband acoustic backscatter from zooplankton in an in situ mesocosm Dunn, Muriel Barbara McGowan-Yallop, Chelsey Pedersen, Geir Falk-Petersen, Stig Daase, Malin Hildegard Elisabeth Last, Kim Langbehn, Tom Fielding, Sophie Brierley, Andrew S. Cottier, Finlo Robert Basedow, Sünnje Linnéa Camus, Lionel Geoffroy, Maxime 2023 application/pdf https://hdl.handle.net/11250/3106811 https://doi.org/10.1093/icesjms/fsad192 eng eng Norges forskningsråd: 329305 Norges forskningsråd: 322332 Norges forskningsråd: 309512 Norges forskningsråd: 300333 ICES Journal of Marine Science. 2023, . urn:issn:1054-3139 https://hdl.handle.net/11250/3106811 https://doi.org/10.1093/icesjms/fsad192 cristin:2210390 14 ICES Journal of Marine Science Peer reviewed Journal article 2023 ftimr https://doi.org/10.1093/icesjms/fsad192 2023-12-13T23:47:43Z Classification of zooplankton to species with broadband echosounder data could increase the taxonomic resolution of acoustic surveys and reduce the dependence on net and trawl samples for ‘ground truthing’. Supervised classification with broadband echosounder data is limited by the acquisition of validated data required to train machine learning algorithms (‘classifiers’). We tested the hypothesis that acoustic scattering models could be used to train classifiers for remote classification of zooplankton. Three classifiers were trained with data from scattering models of four Arctic zooplankton groups (copepods, euphausiids, chaetognaths, and hydrozoans). We evaluated classifier predictions against observations of a mixed zooplankton community in a submerged purpose-built mesocosm (12 m3) insonified with broadband transmissions (185–255 kHz). The mesocosm was deployed from a wharf in Ny-Ålesund, Svalbard, during the Arctic polar night in January 2022. We detected 7722 tracked single targets, which were used to evaluate the classifier predictions of measured zooplankton targets. The classifiers could differentiate copepods from the other groups reasonably well, but they could not differentiate euphausiids, chaetognaths, and hydrozoans reliably due to the similarities in their modelled target spectra. We recommend that model-informed classification of zooplankton from broadband acoustic signals be used with caution until a better understanding of in situ target spectra variability is gained. publishedVersion Article in Journal/Newspaper Arctic Ny Ålesund Ny-Ålesund polar night Svalbard Zooplankton Copepods Institute for Marine Research: Brage IMR Arctic Ny-Ålesund Svalbard ICES Journal of Marine Science |
institution |
Open Polar |
collection |
Institute for Marine Research: Brage IMR |
op_collection_id |
ftimr |
language |
English |
description |
Classification of zooplankton to species with broadband echosounder data could increase the taxonomic resolution of acoustic surveys and reduce the dependence on net and trawl samples for ‘ground truthing’. Supervised classification with broadband echosounder data is limited by the acquisition of validated data required to train machine learning algorithms (‘classifiers’). We tested the hypothesis that acoustic scattering models could be used to train classifiers for remote classification of zooplankton. Three classifiers were trained with data from scattering models of four Arctic zooplankton groups (copepods, euphausiids, chaetognaths, and hydrozoans). We evaluated classifier predictions against observations of a mixed zooplankton community in a submerged purpose-built mesocosm (12 m3) insonified with broadband transmissions (185–255 kHz). The mesocosm was deployed from a wharf in Ny-Ålesund, Svalbard, during the Arctic polar night in January 2022. We detected 7722 tracked single targets, which were used to evaluate the classifier predictions of measured zooplankton targets. The classifiers could differentiate copepods from the other groups reasonably well, but they could not differentiate euphausiids, chaetognaths, and hydrozoans reliably due to the similarities in their modelled target spectra. We recommend that model-informed classification of zooplankton from broadband acoustic signals be used with caution until a better understanding of in situ target spectra variability is gained. publishedVersion |
format |
Article in Journal/Newspaper |
author |
Dunn, Muriel Barbara McGowan-Yallop, Chelsey Pedersen, Geir Falk-Petersen, Stig Daase, Malin Hildegard Elisabeth Last, Kim Langbehn, Tom Fielding, Sophie Brierley, Andrew S. Cottier, Finlo Robert Basedow, Sünnje Linnéa Camus, Lionel Geoffroy, Maxime |
spellingShingle |
Dunn, Muriel Barbara McGowan-Yallop, Chelsey Pedersen, Geir Falk-Petersen, Stig Daase, Malin Hildegard Elisabeth Last, Kim Langbehn, Tom Fielding, Sophie Brierley, Andrew S. Cottier, Finlo Robert Basedow, Sünnje Linnéa Camus, Lionel Geoffroy, Maxime Model-informed classification of broadband acoustic backscatter from zooplankton in an in situ mesocosm |
author_facet |
Dunn, Muriel Barbara McGowan-Yallop, Chelsey Pedersen, Geir Falk-Petersen, Stig Daase, Malin Hildegard Elisabeth Last, Kim Langbehn, Tom Fielding, Sophie Brierley, Andrew S. Cottier, Finlo Robert Basedow, Sünnje Linnéa Camus, Lionel Geoffroy, Maxime |
author_sort |
Dunn, Muriel Barbara |
title |
Model-informed classification of broadband acoustic backscatter from zooplankton in an in situ mesocosm |
title_short |
Model-informed classification of broadband acoustic backscatter from zooplankton in an in situ mesocosm |
title_full |
Model-informed classification of broadband acoustic backscatter from zooplankton in an in situ mesocosm |
title_fullStr |
Model-informed classification of broadband acoustic backscatter from zooplankton in an in situ mesocosm |
title_full_unstemmed |
Model-informed classification of broadband acoustic backscatter from zooplankton in an in situ mesocosm |
title_sort |
model-informed classification of broadband acoustic backscatter from zooplankton in an in situ mesocosm |
publishDate |
2023 |
url |
https://hdl.handle.net/11250/3106811 https://doi.org/10.1093/icesjms/fsad192 |
geographic |
Arctic Ny-Ålesund Svalbard |
geographic_facet |
Arctic Ny-Ålesund Svalbard |
genre |
Arctic Ny Ålesund Ny-Ålesund polar night Svalbard Zooplankton Copepods |
genre_facet |
Arctic Ny Ålesund Ny-Ålesund polar night Svalbard Zooplankton Copepods |
op_source |
14 ICES Journal of Marine Science |
op_relation |
Norges forskningsråd: 329305 Norges forskningsråd: 322332 Norges forskningsråd: 309512 Norges forskningsråd: 300333 ICES Journal of Marine Science. 2023, . urn:issn:1054-3139 https://hdl.handle.net/11250/3106811 https://doi.org/10.1093/icesjms/fsad192 cristin:2210390 |
op_doi |
https://doi.org/10.1093/icesjms/fsad192 |
container_title |
ICES Journal of Marine Science |
_version_ |
1787422274353102848 |