Evaluating the performance of automated detection systems for long-term monitoring of delphinids in diverse marine soundscapes
PLOS One · 2025
DOI: 10.1371/journal.pone.0323768 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Ellen L White und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Ocean and Earth Science, University of Southampton, Southampton, United Kingdom. Hauptthemen laut MEDLINE: Dolphins, Environmental Monitoring, Vocalization, Animal. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Environment Research Council, Interreg North-West Europe.
Abstract (Originalsprache)
There is an increasing reliance on passive acoustic monitoring (PAM) as a cost-effective method for monitoring cetaceans, necessitating robust and efficient automated tools for extracting species presence. This work compares two methods, one based on the ‘off-line’ analysis of raw PAM data, using Convolutional Neural Networks (CNNs), and the second based on in-situ detections, implemented within the C-POD. The C-POD is a rapid, low-cost choice for monitoring of odontocetes, while CNNs, requiring large efforts to train, are gaining traction within bioacoustics as they offer performance benefits above standard detection and classification tools. This work represents the first empirical comparison of a C-POD with a system using a CNN on recorded raw acoustic data for monitoring delphinids. The comparison is based on 3000 hours of PAM data, collected off the west coast of Scotland, using a collocated C-POD and SoundTrap acoustic recorder. Results show that the system using a CNN achieves an overall accuracy of 0.82, and an effectiveness (F1-Score) of 0.78 as a click detector, whilst the C-POD achieves scores of 0.71 and 0.62, respectively. The method employing a CNN provides a lower missed detection rate, with the C-POD failing to detect > 90% delphinid positive hours at one focal site. However, the C-POD offered a lower false-positive rate across all analysis sites. This work highlights the importance of incorporating the right automated tools for long-term species monitoring, as the C-POD offers high precision rates for click detections, while the CNN based system provides a robust approach to identifying seasonal and diurnal trends in long-term dolphin occurrence.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Ocean and Earth Science, University of Southampton, Southampton, United Kingdom.
- Institute of Sound and Vibration, University of Southampton, Southampton, United Kingdom.
- Marine Science Department, Scottish Association of Marine Science, Oban, United Kingdom.
- Renewables and Ecology Group, Marine Directorate, Scottish Government, United Kingdom.
- Agri-Food and Biosciences Institute, Fisheries and Aquatic Ecosystems Branch, Northern Ireland, United Kingdom.
ORCID-Profile: Ellen L White, Paul R White
Förderung
- Natural Environment Research Council
- Interreg North-West Europe
Zitieren
APA
White, E. L., White, P. R., Bull, J. M., Risch, D., Quer, S., & Beck, S. (2025). Evaluating the performance of automated detection systems for long-term monitoring of delphinids in diverse marine soundscapes. PLOS One. https://doi.org/10.1371/journal.pone.0323768
Vancouver
White EL, White PR, Bull JM, Risch D, Quer S, Beck S. Evaluating the performance of automated detection systems for long-term monitoring of delphinids in diverse marine soundscapes. PLOS One. 2025. doi:10.1371/journal.pone.0323768
BibTeX
@article{White2025,
author = {White, Ellen L and White, Paul R and Bull, Jonathan M and Risch, Denise and Quer, Susanna and Beck, Suzanne},
title = {Evaluating the performance of automated detection systems for long-term monitoring of delphinids in diverse marine soundscapes},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0323768}
}
EUVIMED