loading page

Deep learning for passive acoustic monitoring: how to study changing phenology in remote areas
  • +21
  • Sylvain Christin,
  • Éric Hervet,
  • Paul Smith,
  • Ray Alisauskas,
  • Dominique Berteaux,
  • Glen Brown,
  • Kyle Elliott,
  • Jannik Hansen,
  • Sandra Lai,
  • Jean-François Lamarre,
  • Richard Lanctot,
  • Christopher Latty,
  • Audrey Le Pogam,
  • Douglas MacNearney,
  • Vijay Patil,
  • Jennie Rausch,
  • Sarah Saalfeld,
  • Niels Schmidt,
  • Andrew Tam,
  • François Vézina,
  • Øystein Varpe,
  • Paul Woodard,
  • Glenn Yannic,
  • Nicolas Lecomte
Sylvain Christin
University of Moncton

Corresponding Author:[email protected]

Author Profile
Éric Hervet
Université de Moncton
Author Profile
Paul Smith
Environment and Climate Change Canada National Wildlife Research Centre
Author Profile
Ray Alisauskas
Environment and Climate Change Canada
Author Profile
Dominique Berteaux
Universite du Quebec a Rimouski
Author Profile
Glen Brown
Ontario Ministry of Natural Resources
Author Profile
Kyle Elliott
McGill University
Author Profile
Jannik Hansen
Aarhus Universitet
Author Profile
Sandra Lai
Universite du Quebec a Rimouski
Author Profile
Jean-François Lamarre
Polar Knowledge Canada
Author Profile
Richard Lanctot
US Fish and Wildlife Service
Author Profile
Christopher Latty
National Wildlife Refuge
Author Profile
Audrey Le Pogam
Université du Québec à Rimouski
Author Profile
Douglas MacNearney
Environment and Climate Change Canada National Wildlife Research Centre
Author Profile
Vijay Patil
US Geological Survey Alaska Region
Author Profile
Jennie Rausch
Environment and Climate Change Canada Canadian Wildlife Service
Author Profile
Sarah Saalfeld
US Fish and Wildlife Service Alaska Region
Author Profile
Niels Schmidt
Aarhus Universitet
Author Profile
Andrew Tam
Universite du Quebec a Rimouski
Author Profile
François Vézina
Universite du Quebec a Rimouski
Author Profile
Øystein Varpe
University of Bergen
Author Profile
Paul Woodard
Environment and Climate Change Canada Canadian Wildlife Service
Author Profile
Glenn Yannic
Universite Grenoble Alpes
Author Profile
Nicolas Lecomte
Universite de Moncton
Author Profile

Abstract

Understanding how species adjust to seasonality is fundamental in ecology, especially with rapidly increasing global air temperatures. Bioacoustic monitoring offers promise for tracking shifts in seasonal timing of vocal species, as recent automated sound recorders enable large-scale and long-term data collection. Yet, analyzing vast datasets necessitates automation and innovative detection methods. Here, we introduce BioSoundNet, a deep learning model designed for bird vocalization detection. Trained on field data and open-access databases, BioSoundNet achieved AUC scores of 0.88-0.93 and average precisions of 0.87-0.97 across five datasets spanning various ecosystems, and effectively captured the temporal patterns of avian acoustic activity at different time scales. Our findings underline the importance of evaluating models in ecological contexts and to address the potential consequences of missing detections. Operating efficiently on standard computers, BioSoundNet is a robust tool for automated bird vocalization detection, providing a valuable resource for ecological phenology studies and acoustic dataset analysis.
09 Nov 2023Submitted to Ecology Letters
10 Nov 2023Submission Checks Completed
10 Nov 2023Assigned to Editor
10 Nov 2023Review(s) Completed, Editorial Evaluation Pending
20 Nov 2023Reviewer(s) Assigned