Comparing neural networks against click train detectors to reveal temporal trends in passive acoustic sperm whale detections
The Journal of the Acoustical Society of America · 2024
DOI: 10.1121/10.0034602 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift The Journal of the Acoustical Society of America, 2024. Verfasst von Laia Garrobé Fonollosa und 6 weiteren Autor:innen. Beteiligte Einrichtung: Sea Mammal Research Unit, School of Biology, University of St Andrews, KY16 9TH, St Andrews, United Kingdom. Hauptthemen laut MEDLINE: Sperm Whale, Vocalization, Animal, Acoustics. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 60 Literaturangaben.
Abstract (Originalsprache)
Passive acoustic monitoring (PAM) is an increasingly popular tool to study vocalising species. The amount of data generated by PAM studies calls for robust automatic classifiers. Deep learning (DL) techniques have been proven effective in identifying acoustic signals in challenging datasets, but due to their black-box nature their underlying biases are hard to quantify. This study compares human analyst annotations, a multi-hypothesis tracking (MHT) click train classifier and a DL-based acoustic classifier to classify acoustic recordings based on the presence or absence of sperm whale (Physeter macrocephalus) click trains and study the temporal and spatial distributions of the Mediterranean sperm whale subpopulation around the Balearic Islands. The MHT and DL classifiers showed agreements with human labels of 85.7% and 85.0%, respectively, on data from sites they were trained on, but both saw a drop in performance when deployed on a new site. Agreement rates between classifiers surpassed those between human experts. Modeled seasonal and diel variations in sperm whale detections for both classifiers showed compatible results, revealing an increase in occurrence and diurnal activity during the summer and autumn months. This study highlights the strengths and limitations of two automatic classification algorithms to extract biologically useful information from large acoustic datasets.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Sea Mammal Research Unit, School of Biology, University of St Andrews, KY16 9TH, St Andrews, United Kingdom.
- The Scottish Association for Marine Science (SAMS), Oban, PA37 1QA, Scotland, United Kingdom.
- Asociación Tursiops, Palma de Mallorca, Balearic Islands, Spain.
- Centre for Research into Ecological and Environmental Modelling, University of St Andrews, St Andrews, United Kingdom.
ORCID-Profile: Laia Garrobé Fonollosa, Thomas Webber, Douglas Gillespie, Enrico Pirotta, Luke Rendell
Zitieren
APA
Garrobé Fonollosa, L., Webber, T., Brotons, J. M., Cerdà, M., Gillespie, D., Pirotta, E., & Rendell, L. (2024). Comparing neural networks against click train detectors to reveal temporal trends in passive acoustic sperm whale detections. The Journal of the Acoustical Society of America. https://doi.org/10.1121/10.0034602
Vancouver
Garrobé Fonollosa L, Webber T, Brotons JM, Cerdà M, Gillespie D, Pirotta E, et al. Comparing neural networks against click train detectors to reveal temporal trends in passive acoustic sperm whale detections. The Journal of the Acoustical Society of America. 2024. doi:10.1121/10.0034602
BibTeX
@article{GarrobFonollosa2024,
author = {Garrobé Fonollosa, Laia and Webber, Thomas and Brotons, José Maria and Cerdà, Margalida and Gillespie, Douglas and Pirotta, Enrico and Rendell, Luke},
title = {Comparing neural networks against click train detectors to reveal temporal trends in passive acoustic sperm whale detections},
journal = {The Journal of the Acoustical Society of America},
year = {2024},
doi = {10.1121/10.0034602}
}
EUVIMED