Open-source workflow approaches to passive acoustic monitoring of bats
The work was funded by grants to PTM from Carlsberg Semper Ardens Research Projects and the Independent Research Fund Denmark. The affordability, storage and power capacity of compact modern recording hardware have evolved passive acoustic monitoring (PAM) of animals and soundscapes into a non-invas...
Published in: | Methods in Ecology and Evolution |
---|---|
Main Authors: | , , , , , , |
Other Authors: | |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | http://hdl.handle.net/10023/27683 https://doi.org/10.1111/2041-210X.14131 |
id |
ftstandrewserep:oai:research-repository.st-andrews.ac.uk:10023/27683 |
---|---|
record_format |
openpolar |
spelling |
ftstandrewserep:oai:research-repository.st-andrews.ac.uk:10023/27683 2023-07-02T03:33:52+02:00 Open-source workflow approaches to passive acoustic monitoring of bats Brinkløv, Signe M. M. Macaulay, Jamie Bergler, Christian Tougaard, Jakob Beedholm, Kristian Elmeros, Morten Madsen, Peter Teglberg University of St Andrews. School of Biology 2023-05-26T11:30:05Z 17 application/pdf http://hdl.handle.net/10023/27683 https://doi.org/10.1111/2041-210X.14131 eng eng Methods in Ecology and Evolution Brinkløv , S M M , Macaulay , J , Bergler , C , Tougaard , J , Beedholm , K , Elmeros , M & Madsen , P T 2023 , ' Open-source workflow approaches to passive acoustic monitoring of bats ' , Methods in Ecology and Evolution , vol. Early View . https://doi.org/10.1111/2041-210X.14131 2041-210X PURE: 286647332 PURE UUID: af304c52-246e-4ec8-a907-8c70a29fe17d RIS: urn:D4438D919E4AAEA9495A42DA920C78D2 http://hdl.handle.net/10023/27683 https://doi.org/10.1111/2041-210X.14131 Copyright © 2023 The Authors. Methods in Ecology and Evolution published by John Wiley & Sons Ltd on behalf of British Ecological Society. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes. Automated Bat Classification Deep learning Detection Echolocation Open source Passive acoustic monitoring DAS MCP Journal article 2023 ftstandrewserep https://doi.org/10.1111/2041-210X.14131 2023-06-13T18:29:09Z The work was funded by grants to PTM from Carlsberg Semper Ardens Research Projects and the Independent Research Fund Denmark. The affordability, storage and power capacity of compact modern recording hardware have evolved passive acoustic monitoring (PAM) of animals and soundscapes into a non-invasive, cost-effective tool for research and ecological management particularly useful for bats and toothed whales that orient and forage using ultrasonic echolocation. The use of PAM at large scales hinges on effective automated detectors and species classifiers which, combined with distance sampling approaches, have enabled species abundance estimation of toothed whales. But standardized, user-friendly and open access automated detection and classification workflows are in demand for this key conservation metric to be realized for bats. We used the PAMGuard toolbox including its new deep learning classification module to test the performance of four open-source workflows for automated analyses of acoustic datasets from bats. Each workflow used a different initial detection algorithm followed by the same deep learning classification algorithm and was evaluated against the performance of an expert manual analyst. Workflow performance depended strongly on the signal-to-noise ratio and detection algorithm used: the full deep learning workflow had the best classification accuracy (≤67%) but was computationally too slow for practical large-scale bat PAM. Workflows using PAMGuard's detection module or triggers onboard an SM4BAT or AudioMoth accurately classified up to 47%, 59% and 34%, respectively, of calls to species. Not all workflows included noise sampling critical to estimating changes in detection probability over time, a vital parameter for abundance estimation. The workflow using PAMGuard's detection module was 40 times faster than the full deep learning workflow and missed as few calls (recall for both ~0.6), thus balancing computational speed and performance. We show that complete acoustic detection and ... Article in Journal/Newspaper toothed whales University of St Andrews: Digital Research Repository Methods in Ecology and Evolution |
institution |
Open Polar |
collection |
University of St Andrews: Digital Research Repository |
op_collection_id |
ftstandrewserep |
language |
English |
topic |
Automated Bat Classification Deep learning Detection Echolocation Open source Passive acoustic monitoring DAS MCP |
spellingShingle |
Automated Bat Classification Deep learning Detection Echolocation Open source Passive acoustic monitoring DAS MCP Brinkløv, Signe M. M. Macaulay, Jamie Bergler, Christian Tougaard, Jakob Beedholm, Kristian Elmeros, Morten Madsen, Peter Teglberg Open-source workflow approaches to passive acoustic monitoring of bats |
topic_facet |
Automated Bat Classification Deep learning Detection Echolocation Open source Passive acoustic monitoring DAS MCP |
description |
The work was funded by grants to PTM from Carlsberg Semper Ardens Research Projects and the Independent Research Fund Denmark. The affordability, storage and power capacity of compact modern recording hardware have evolved passive acoustic monitoring (PAM) of animals and soundscapes into a non-invasive, cost-effective tool for research and ecological management particularly useful for bats and toothed whales that orient and forage using ultrasonic echolocation. The use of PAM at large scales hinges on effective automated detectors and species classifiers which, combined with distance sampling approaches, have enabled species abundance estimation of toothed whales. But standardized, user-friendly and open access automated detection and classification workflows are in demand for this key conservation metric to be realized for bats. We used the PAMGuard toolbox including its new deep learning classification module to test the performance of four open-source workflows for automated analyses of acoustic datasets from bats. Each workflow used a different initial detection algorithm followed by the same deep learning classification algorithm and was evaluated against the performance of an expert manual analyst. Workflow performance depended strongly on the signal-to-noise ratio and detection algorithm used: the full deep learning workflow had the best classification accuracy (≤67%) but was computationally too slow for practical large-scale bat PAM. Workflows using PAMGuard's detection module or triggers onboard an SM4BAT or AudioMoth accurately classified up to 47%, 59% and 34%, respectively, of calls to species. Not all workflows included noise sampling critical to estimating changes in detection probability over time, a vital parameter for abundance estimation. The workflow using PAMGuard's detection module was 40 times faster than the full deep learning workflow and missed as few calls (recall for both ~0.6), thus balancing computational speed and performance. We show that complete acoustic detection and ... |
author2 |
University of St Andrews. School of Biology |
format |
Article in Journal/Newspaper |
author |
Brinkløv, Signe M. M. Macaulay, Jamie Bergler, Christian Tougaard, Jakob Beedholm, Kristian Elmeros, Morten Madsen, Peter Teglberg |
author_facet |
Brinkløv, Signe M. M. Macaulay, Jamie Bergler, Christian Tougaard, Jakob Beedholm, Kristian Elmeros, Morten Madsen, Peter Teglberg |
author_sort |
Brinkløv, Signe M. M. |
title |
Open-source workflow approaches to passive acoustic monitoring of bats |
title_short |
Open-source workflow approaches to passive acoustic monitoring of bats |
title_full |
Open-source workflow approaches to passive acoustic monitoring of bats |
title_fullStr |
Open-source workflow approaches to passive acoustic monitoring of bats |
title_full_unstemmed |
Open-source workflow approaches to passive acoustic monitoring of bats |
title_sort |
open-source workflow approaches to passive acoustic monitoring of bats |
publishDate |
2023 |
url |
http://hdl.handle.net/10023/27683 https://doi.org/10.1111/2041-210X.14131 |
genre |
toothed whales |
genre_facet |
toothed whales |
op_relation |
Methods in Ecology and Evolution Brinkløv , S M M , Macaulay , J , Bergler , C , Tougaard , J , Beedholm , K , Elmeros , M & Madsen , P T 2023 , ' Open-source workflow approaches to passive acoustic monitoring of bats ' , Methods in Ecology and Evolution , vol. Early View . https://doi.org/10.1111/2041-210X.14131 2041-210X PURE: 286647332 PURE UUID: af304c52-246e-4ec8-a907-8c70a29fe17d RIS: urn:D4438D919E4AAEA9495A42DA920C78D2 http://hdl.handle.net/10023/27683 https://doi.org/10.1111/2041-210X.14131 |
op_rights |
Copyright © 2023 The Authors. Methods in Ecology and Evolution published by John Wiley & Sons Ltd on behalf of British Ecological Society. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes. |
op_doi |
https://doi.org/10.1111/2041-210X.14131 |
container_title |
Methods in Ecology and Evolution |
_version_ |
1770273989453676544 |