Deep neural networks for automated detection of marine mammal species
Deep neural networks have advanced the field of detection and classification and allowed for effective identification of signals in challenging data sets. Numerous time-critical conservation needs may benefit from these methods. We developed and empirically studied a variety of deep neural networks...
Published in: | Scientific Reports |
---|---|
Main Authors: | , , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://risweb.st-andrews.ac.uk/portal/en/researchoutput/deep-neural-networks-for-automated-detection-of-marine-mammal-species(f425a62a-030f-4d10-8b4f-cf40476980e8).html https://doi.org/10.1038/s41598-020-57549-y https://research-repository.st-andrews.ac.uk/bitstream/10023/19305/1/Shiu_2020_SR_Deepneural_CC.pdf |
id |
ftunstandrewcris:oai:risweb.st-andrews.ac.uk:publications/f425a62a-030f-4d10-8b4f-cf40476980e8 |
---|---|
record_format |
openpolar |
spelling |
ftunstandrewcris:oai:risweb.st-andrews.ac.uk:publications/f425a62a-030f-4d10-8b4f-cf40476980e8 2023-05-15T16:08:18+02:00 Deep neural networks for automated detection of marine mammal species Shiu, Yu Palmer, Kaitlin Roch, Marie Fleishman, Erica Liu, Xiaobai Nosal, Eva-Marie Helble, Tyler Cholewiak, Danielle Gillespie, Douglas Michael Klinck, Holger 2020-01-17 application/pdf https://risweb.st-andrews.ac.uk/portal/en/researchoutput/deep-neural-networks-for-automated-detection-of-marine-mammal-species(f425a62a-030f-4d10-8b4f-cf40476980e8).html https://doi.org/10.1038/s41598-020-57549-y https://research-repository.st-andrews.ac.uk/bitstream/10023/19305/1/Shiu_2020_SR_Deepneural_CC.pdf eng eng info:eu-repo/semantics/openAccess Shiu , Y , Palmer , K , Roch , M , Fleishman , E , Liu , X , Nosal , E-M , Helble , T , Cholewiak , D , Gillespie , D M & Klinck , H 2020 , ' Deep neural networks for automated detection of marine mammal species ' , Scientific Reports , vol. 10 , 607 . https://doi.org/10.1038/s41598-020-57549-y article 2020 ftunstandrewcris https://doi.org/10.1038/s41598-020-57549-y 2021-12-26T14:36:01Z Deep neural networks have advanced the field of detection and classification and allowed for effective identification of signals in challenging data sets. Numerous time-critical conservation needs may benefit from these methods. We developed and empirically studied a variety of deep neural networks to detect the vocalizations of endangered North Atlantic right whales ( Eubalaena glacialis ). We compared the performance of these deep architectures to that of traditional detection algorithms for the primary vocalization produced by this species, the upcall. We show that deep-learning architectures are capable of producing false-positive rates that are orders of magnitude lower than alternative algorithms while substantially increasing the ability to detect calls. We demonstrate that a deep neural network trained with recordings from a single geographic region recorded over a span of days is capable of generalizing well to data from multiple years and across the species’ range, and that the low false positives make the output of the algorithm amenable to quality control for verification. The deep neural networks we developed are relatively easy to implement with existing software, and may provide new insights applicable to the conservation of endangered species. Article in Journal/Newspaper Eubalaena glacialis North Atlantic University of St Andrews: Research Portal Scientific Reports 10 1 |
institution |
Open Polar |
collection |
University of St Andrews: Research Portal |
op_collection_id |
ftunstandrewcris |
language |
English |
description |
Deep neural networks have advanced the field of detection and classification and allowed for effective identification of signals in challenging data sets. Numerous time-critical conservation needs may benefit from these methods. We developed and empirically studied a variety of deep neural networks to detect the vocalizations of endangered North Atlantic right whales ( Eubalaena glacialis ). We compared the performance of these deep architectures to that of traditional detection algorithms for the primary vocalization produced by this species, the upcall. We show that deep-learning architectures are capable of producing false-positive rates that are orders of magnitude lower than alternative algorithms while substantially increasing the ability to detect calls. We demonstrate that a deep neural network trained with recordings from a single geographic region recorded over a span of days is capable of generalizing well to data from multiple years and across the species’ range, and that the low false positives make the output of the algorithm amenable to quality control for verification. The deep neural networks we developed are relatively easy to implement with existing software, and may provide new insights applicable to the conservation of endangered species. |
format |
Article in Journal/Newspaper |
author |
Shiu, Yu Palmer, Kaitlin Roch, Marie Fleishman, Erica Liu, Xiaobai Nosal, Eva-Marie Helble, Tyler Cholewiak, Danielle Gillespie, Douglas Michael Klinck, Holger |
spellingShingle |
Shiu, Yu Palmer, Kaitlin Roch, Marie Fleishman, Erica Liu, Xiaobai Nosal, Eva-Marie Helble, Tyler Cholewiak, Danielle Gillespie, Douglas Michael Klinck, Holger Deep neural networks for automated detection of marine mammal species |
author_facet |
Shiu, Yu Palmer, Kaitlin Roch, Marie Fleishman, Erica Liu, Xiaobai Nosal, Eva-Marie Helble, Tyler Cholewiak, Danielle Gillespie, Douglas Michael Klinck, Holger |
author_sort |
Shiu, Yu |
title |
Deep neural networks for automated detection of marine mammal species |
title_short |
Deep neural networks for automated detection of marine mammal species |
title_full |
Deep neural networks for automated detection of marine mammal species |
title_fullStr |
Deep neural networks for automated detection of marine mammal species |
title_full_unstemmed |
Deep neural networks for automated detection of marine mammal species |
title_sort |
deep neural networks for automated detection of marine mammal species |
publishDate |
2020 |
url |
https://risweb.st-andrews.ac.uk/portal/en/researchoutput/deep-neural-networks-for-automated-detection-of-marine-mammal-species(f425a62a-030f-4d10-8b4f-cf40476980e8).html https://doi.org/10.1038/s41598-020-57549-y https://research-repository.st-andrews.ac.uk/bitstream/10023/19305/1/Shiu_2020_SR_Deepneural_CC.pdf |
genre |
Eubalaena glacialis North Atlantic |
genre_facet |
Eubalaena glacialis North Atlantic |
op_source |
Shiu , Y , Palmer , K , Roch , M , Fleishman , E , Liu , X , Nosal , E-M , Helble , T , Cholewiak , D , Gillespie , D M & Klinck , H 2020 , ' Deep neural networks for automated detection of marine mammal species ' , Scientific Reports , vol. 10 , 607 . https://doi.org/10.1038/s41598-020-57549-y |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.1038/s41598-020-57549-y |
container_title |
Scientific Reports |
container_volume |
10 |
container_issue |
1 |
_version_ |
1766404357439356928 |