EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Unlocking the soundscape of coral reefs with artificial intelligence: pretrained networks and unsupervised learning win out

Ben Williams iD, Santiago M Balvanera, Sarab S Sethi, Timothy A C Lamont, Jamaluddin Jompa, Mochyudho Prasetya, Laura Richardson, Lucille Chapuis iD, Emma Weschke, Andrew Hoey, Ricardo Beldade, Suzanne C Mills und 5 weitere

PLOS Computational Biology · 2025

DOI: 10.1371/journal.pcbi.1013029 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2025. Verfasst von Ben Williams und 16 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, University College London, London, United Kingdo…. Hauptthemen laut MEDLINE: Coral Reefs, Unsupervised Machine Learning, Artificial Intelligence. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fisheries Society of the British Isles, Natural Environment Research Council Research, Natural Environment Research Council–Australian Institute of Marine Science CASE GW4+ Studentship.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Passive acoustic monitoring can offer insights into the state of coral reef ecosystems at low-costs and over extended temporal periods. Comparison of whole soundscape properties can rapidly deliver broad insights from acoustic data, in contrast to detailed but time-consuming analysis of individual bioacoustic events. However, a lack of effective automated analysis for whole soundscape data has impeded progress in this field. Here, we show that machine learning (ML) can be used to unlock greater insights from reef soundscapes. We showcase this on a diverse set of tasks using three biogeographically independent datasets, each containing fish community (high or low), coral cover (high or low) or depth zone (shallow or mesophotic) classes. We show supervised learning can be used to train models that can identify ecological classes and individual sites from whole soundscapes. However, we report unsupervised clustering achieves this whilst providing a more detailed understanding of ecological and site groupings within soundscape data. We also compare three different approaches for extracting feature embeddings from soundscape recordings for input into ML algorithms: acoustic indices commonly used by soundscape ecologists, a pretrained convolutional neural network (P-CNN) trained on 5.2 million hrs of YouTube audio, and CNN’s which were trained on each individual task (T-CNN). Although the T-CNN performs marginally better across tasks, we reveal that the P-CNN offers a powerful tool for generating insights from marine soundscape data as it requires orders of magnitude less computational resources whilst achieving near comparable performance to the T-CNN, with significant performance improvements over the acoustic indices. Our findings have implications for soundscape ecology in any habitat.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Coral ReefsUnsupervised Machine LearningArtificial IntelligenceAnimalsAcousticsEcosystemAlgorithmsNeural Networks, ComputerComputational BiologyFishesMachine LearningEnvironmental Monitoring

Autor:innen und Institutionen

  • Centre for Biodiversity and Environment Research, Department of Genetics, Evolution and Environment, University College London, London, United Kingdom.
  • Zoological Society of London, Regents Park, London, United Kingdom.
  • Department of Life Sciences, Imperial College London, London, United Kingdom.
  • Lancaster Environment Centre, Lancaster University, Lancaster, United Kingdom.
  • Graduate School, Universitas Hasanuddin, Makassar, Indonesia.
  • MARS Sustainable Solutions, Makassar, Indonesia.

ORCID-Profile: Ben Williams, Lucille Chapuis

Förderung

  • Fisheries Society of the British Isles
  • Natural Environment Research Council Research
  • Natural Environment Research Council–Australian Institute of Marine Science CASE GW4+ Studentship
  • Royal Commission for the Exhibition of 1851 Research Fellowship
  • Swiss National Science Foundation
  • Fisheries Society of the Bristish Isles
  • Natural Environment Research Council
  • Royal Commission for the Exhibition of 1851

Zitieren

APA

Williams, B., Balvanera, S. M., Sethi, S. S., Lamont, T. A. C., Jompa, J., Prasetya, M., Richardson, L., Chapuis, L., Weschke, E., Hoey, A., Beldade, R., Mills, S. C., Haguenauer, A., Zuberer, F., Simpson, S. D., Curnick, D., & Jones, K. E. (2025). Unlocking the soundscape of coral reefs with artificial intelligence: pretrained networks and unsupervised learning win out. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1013029

Vancouver

Williams B, Balvanera SM, Sethi SS, Lamont TAC, Jompa J, Prasetya M, et al. Unlocking the soundscape of coral reefs with artificial intelligence: pretrained networks and unsupervised learning win out. PLOS Computational Biology. 2025. doi:10.1371/journal.pcbi.1013029

BibTeX
@article{Williams2025,
  author = {Williams, Ben and Balvanera, Santiago M and Sethi, Sarab S and Lamont, Timothy A C and Jompa, Jamaluddin and Prasetya, Mochyudho and Richardson, Laura and Chapuis, Lucille and Weschke, Emma and Hoey, Andrew and Beldade, Ricardo and Mills, Suzanne C and Haguenauer, Anne and Zuberer, Frederic and Simpson, Stephen D and Curnick, David and Jones, Kate E},
  title = {Unlocking the soundscape of coral reefs with artificial intelligence: pretrained networks and unsupervised learning win out},
  journal = {PLOS Computational Biology},
  year = {2025},
  doi = {10.1371/journal.pcbi.1013029}
}
Kostenlos starten →