Automated detection of fin whales with distributed acoustic sensing in the Arctic and Mediterranean
The Journal of the Acoustical Society of America · 01.12.2025 · 158 (6) · 5057-5074
DOI: 10.1121/10.0041855 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 29.12.2025. Verfasst von Khanh Truong und 5 weiteren Autor:innen. Beteiligte Einrichtung: Norwegian University of Science and Technology, Trondheim, Norway. Hauptthemen laut MEDLINE: Fin Whale, Vocalization, Animal, Acoustics, Environmental Monitoring. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: SFI Offshore Mechatronics, H2020 Marie Skłodowska-Curie Actions, Agence Nationale de la Recherche.
Abstract (Originalsprache)
The fin whale is a key species in marine ecosystems and a sensitive indicator of ocean health. Yet monitoring its low-frequency calls at scale remains challenging. Distributed acoustic sensing (DAS) on subsea fiber cables can record thousands of calls daily, but these are hidden in terabytes of data, demanding automated detection. This study presents a three-stage pipeline: (i) data enhancement using frequency-wavenumber and root-mean-square filtering; (ii) call detection in the time-space domain using four approaches: line-based detection (Hough transform, HT), density-based clustering (DBSCAN), template matching combined with clustering (TM), and a deep-learning-based detector (YOLO); and (iii) detection refinement using hyperbola fitting and a LightGBM classifier. The pipeline is evaluated on datasets from two submarine cables: 135 km in Svalbard, Norway, and 162 km between Monaco and Italy. YOLO achieves the highest F1 score (0.89) on the Svalbard dataset, outperforming HT (0.57), DBSCAN (0.43), and TM (0.71). Without fine-tuning, YOLO also achieves a high F1 score (0.80) on the Monaco–Italy dataset, demonstrating robust generalization across geographic locations and seafloor environments. These results highlight DAS combined with deep learning as a powerful tool for scalable, real-time monitoring of marine mammal vocalizations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Norwegian University of Science and Technology, Trondheim, Norway.
- Alcatel Submarine Networks Norway AS, Trondheim, Norway.
- Université Côte d'Azur, CNRS, Observatoire de la Côte d'Azur, IRD, Géoazur, Valbonne, France.
ORCID-Profile: Khanh Truong, Jo Eidsvik, Robin Andre Rørstadbotnen, Jan Petter Morten, Anthony Sladen
Förderung
- SFI Offshore Mechatronics
- H2020 Marie Skłodowska-Curie Actions
- Agence Nationale de la Recherche
Zitieren
APA
Truong, K., Eidsvik, J., Rørstadbotnen, R. A., Morten, J. P., Andres, L., & Sladen, A. (2025). Automated detection of fin whales with distributed acoustic sensing in the Arctic and Mediterranean. The Journal of the Acoustical Society of America, 158(6), 5057-5074. https://doi.org/10.1121/10.0041855
Vancouver
Truong K, Eidsvik J, Rørstadbotnen RA, Morten JP, Andres L, Sladen A. Automated detection of fin whales with distributed acoustic sensing in the Arctic and Mediterranean. The Journal of the Acoustical Society of America. 2025;158(6):5057-5074. doi:10.1121/10.0041855
BibTeX
@article{Truong2025,
author = {Truong, Khanh and Eidsvik, Jo and Rørstadbotnen, Robin Andre and Morten, Jan Petter and Andres, Laurine and Sladen, Anthony},
title = {Automated detection of fin whales with distributed acoustic sensing in the Arctic and Mediterranean},
journal = {The Journal of the Acoustical Society of America},
year = {2025},
volume = {158},
number = {6},
pages = {5057--5074},
doi = {10.1121/10.0041855}
}
EUVIMED