Bat detective-Deep learning tools for bat acoustic signal detection

Oisin Mac Aodha; Rory Gibb; Kate E Barlow; Ella Browning; Michael Firman; Robin Freeman; Briana Harder; Libby Kinsey; Gary R Mead; Stuart E Newson; Ivan Pandourski; Stuart Parsons; Jon Russ; Abigel Szodoray-Paradi; Farkas Szodoray-Paradi; Elena Tilova; Mark Girolami; Gabriel Brostow; Kate E Jones

doi:10.1371/journal.pcbi.1005995

Back

Bat detective-Deep learning tools for bat acoustic signal detection

Journal article

Open access

Peer reviewed

Bat detective-Deep learning tools for bat acoustic signal detection

Oisin Mac Aodha, Rory Gibb, Kate E Barlow, Ella Browning, Michael Firman, Robin Freeman, Briana Harder, Libby Kinsey, Gary R Mead, Stuart E Newson, …

PLoS Computational Biology, Vol.14(3), pp.1-12

2018

DOI: https://doi.org/10.1371/journal.pcbi.1005995

PMCID: PMC5843167

PMID: 29518076

Files and links (2)

pdf

Bat detective-Deep learning tools for bat acoustic signal detection4.64 MBDownload View

Published VersionCC BY V4.0, Open Access

url

https://doi.org/10.1371/journal.pcbi.1005995View

Published Version

Related material

Has preprint

Bat Detective - Deep Learning Tools for Bat Acoustic Signal Detection

Abstract

Passive acoustic sensing has emerged as a powerful tool for quantifying anthropogenic impacts on biodiversity, especially for echolocating bat species. To better assess bat population trends there is a critical need for accurate, reliable, and open source tools that allow the detection and classification of bat calls in large collections of audio recordings. The majority of existing tools are commercial or have focused on the species classification task, neglecting the important problem of first localizing echolocation calls in audio which is particularly problematic in noisy recordings. We developed a convolutional neural network based open-source pipeline for detecting ultrasonic, full-spectrum, search-phase calls produced by echolocating bats. Our deep learning algorithms were trained on full-spectrum ultrasonic audio collected along road-transects across Europe and labelled by citizen scientists from www.batdetective.org. When compared to other existing algorithms and commercial systems, we show significantly higher detection performance of search-phase echolocation calls with our test sets. As an example application, we ran our detection pipeline on bat monitoring data collected over five years from Jersey (UK), and compared results to a widely-used commercial system. Our detection pipeline can be used for the automatic detection and monitoring of bat populations, and further facilitates their use as indicator species on a large scale. Our proposed pipeline makes only a small number of bat specific design decisions, and with appropriate training data it could be applied to detecting other species in audio. A crucial novelty of our work is showing that with careful, non-trivial, design and implementation considerations, state-of-the-art deep learning methods can be used for accurate and efficient monitoring in audio.

Details

Title: Bat detective-Deep learning tools for bat acoustic signal detection
Authors: Oisin Mac Aodha (Author) - University College London
Rory Gibb (Author) - University College London
Kate E Barlow (Author) - Bat Conservation Trust
Ella Browning (Author) - Zoological Society of London
Michael Firman (Author) - University College London
Robin Freeman (Author) - Zoological Society of London
Briana Harder (Author) - Bellevue, Washington, United States of America
Libby Kinsey (Author) - University College London
Gary R Mead (Author) - Wickford, Essex, United Kingdom
Stuart E Newson (Author) - British Trust for Ornithology
Ivan Pandourski (Author) - Institute of Biodiversity and Ecosystem Research
Stuart Parsons (Author) - Queensland University of Technology
Jon Russ (Author) - Ridgeway Ecology Ltd
Abigel Szodoray-Paradi (Author) - Romanian Bat Protection Association, Satu Mare, Romania
Farkas Szodoray-Paradi (Author) - Romanian Bat Protection Association, Satu Mare, Romania
Elena Tilova (Author) - Green Balkans-Stara Zagora, Stara Zagora, Bulgaria
Mark Girolami (Author) - Imperial College London
Gabriel Brostow (Author) - University College London
Kate E Jones (Author) - University College London
Publication details: PLoS Computational Biology, Vol.14(3), pp.1-12
Publisher: Public Library of Science
Date published: 2018
DOI: 10.1371/journal.pcbi.1005995
ISSN: 1553-7358
PMID: 29518076; PMC5843167
Copyright note: Copyright: © 2018 Mac Aodha et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Organisation Unit: University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering
Language: English
Record Identifier: 99575106902621
Output Type: Journal article

Metrics

4 File views/ downloads

32 Record Views

150 Times Cited - Web of Science

See more details

InCites Highlights

These are selected metrics from InCites Benchmarking & Analytics tool, related to this output

Collaboration types: Domestic collaboration; International collaboration
Web Of Science research areas: Biochemical Research Methods; Mathematical & Computational Biology

UN Sustainable Development Goals (SDGs)

This output has contributed to the advancement of the following goals:

Source: InCites