CoChat
Sign Up
Cited by 218Bat Biology and Ecology StudiesMusic and Audio ProcessingAnimal Vocal Communication and Behavior

The DOI matches its Crossref record; 62 of the 64 references it cites were found in a registry or an index.

Bat detective—Deep learning tools for bat acoustic signal detection

Open access
Mac Aodha, Oisin, Gibb, Rory, Barlow, Kate E., Browning, Ella, Firman, Michael, Freeman, Robin, Harder, Briana, Kinsey, Libby, Mead, Gary R., Newson, Stuart E., Pandourski, Ivan, Parsons, Stuart, Russ, Jon, Szodoray-Paradi, Abigel, Szodoray-Paradi, Farkas, Tilova, Elena, Girolami, Mark, Brostow, Gabriel, Jones, Kate E.·2018·PLOS Computational Biology
DOI 10.1371/journal.pcbi.1005995PMC PMC5843167

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1371/journal.pcbi.1005995

Cites

62 of 62 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig 1 Detection pipeline for search-phase bat echolocation calls. (a) Raw audio files are converted into a spectrogram using a Fast Fourier Transform (b). Files are de-noised (c), and a sliding window Convolutional Neural Network (CNN) classifier (d, yellow box) produces a probability for each time step. Individual call detection probabilities using non-maximum suppression are produced (e, green boxes), and the time in file of each prediction along with the classifier probability are exported as text files.
Fig 1 Detection pipeline for search-phase bat echolocation calls. (a) Raw audio files are converted into a spectrogram using a Fast Fourier Transform (b). Files are de-noised (c), and a sliding window Convolutional Neural Network (CNN) classifier (d, yellow box) produces a probability for each time step. Individual call detection probabilities using non-maximum suppression are produced (e, green boxes), and the time in file of each prediction along with the classifier probability are exported as text files.CC BY · PubMed Central
Fig 2 Spatial distribution of the BatDetect CNNs training and testing datasets. (a) Location of training data for all experiments and one test dataset in Romania and Bulgaria (2006–2011) from time-expanded (TE) data recorded along road transects by the Indicator Bats Programme (iBats) [7], where red and black points represent training and test data, respectively. (b) Locations of additional test datasets from TE data recorded as part of iBats car transects in the UK (2005–2011), and from real-time recordings from static recorders from the Norfolk Bat Survey from 2015 (inset). Points represent the start location of each snapshot recording for each iBats transect or locations of static detectors for the Norfolk Bat Survey.
Fig 2 Spatial distribution of the BatDetect CNNs training and testing datasets. (a) Location of training data for all experiments and one test dataset in Romania and Bulgaria (2006–2011) from time-expanded (TE) data recorded along road transects by the Indicator Bats Programme (iBats) [7], where red and black points represent training and test data, respectively. (b) Locations of additional test datasets from TE data recorded as part of iBats car transects in the UK (2005–2011), and from real-time recordings from static recorders from the Norfolk Bat Survey from 2015 (inset). Points represent the start location of each snapshot recording for each iBats transect or locations of static detectors for the Norfolk Bat Survey.CC BY · PubMed Central
Fig 3 Precision-recall curves for bat search-phase call detection algorithms across three testing datasets; (a) iBats Romania and Bulgaria; (b) iBats UK; and (c) Norfolk Bat Survey. Curves were obtained by sweeping the output probability for a given detector algorithm and computing the precision and recall at each threshold. The commercial systems or algorithms that did not return a continuous output or probability (SCAN’R, Segment, and Kaleidoscope) were depicted as a single point.
Fig 3 Precision-recall curves for bat search-phase call detection algorithms across three testing datasets; (a) iBats Romania and Bulgaria; (b) iBats UK; and (c) Norfolk Bat Survey. Curves were obtained by sweeping the output probability for a given detector algorithm and computing the precision and recall at each threshold. The commercial systems or algorithms that did not return a continuous output or probability (SCAN’R, Segment, and Kaleidoscope) were depicted as a single point.CC BY · PubMed Central
Fig 4 Comparison of the predicted bat detections (calls and passes) for two different acoustic systems using monitoring data collected from Jersey, UK. Acoustic systems used were SonoBat (version 3.1.7p) [43] using analysis in [49], and BatDetect CNNFAST using a probability threshold of 0.90. Detections are shown within each box plot, where the black line represents the mean across all transect sampling events from 2011–2015, boxes represent the middle 50% of the data, whiskers represent variability outside the upper and lower quartiles, with outliers plotted as individual points. See text for definition of a bat pass.
Fig 4 Comparison of the predicted bat detections (calls and passes) for two different acoustic systems using monitoring data collected from Jersey, UK. Acoustic systems used were SonoBat (version 3.1.7p) [43] using analysis in [49], and BatDetect CNNFAST using a probability threshold of 0.90. Detections are shown within each box plot, where the black line represents the mean across all transect sampling events from 2011–2015, boxes represent the middle 50% of the data, whiskers represent variability outside the upper and lower quartiles, with outliers plotted as individual points. See text for definition of a bat pass.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 3

  1. Salamon J, Bello JP. Deep convolutional neural networks and data augmentation for environmental sound classification. arXiv preprint arXiv:160804363. 2016.
  2. Goeau H, Glotin H, Vellinga W-P, Planque R, Joly A, editors. LifeCLEF Bird Identification Task 2016. The Arrival of Deep Learning. Working Notes of CLEF 2016-Conference and Labs of the Evaluation forum; 2016; Évora, Portugal.
  3. Walters CL, Browning E, Jones KE. iBats Jersey Review. London, UK: 2016.

Cited by

Sorted by citations

See all 218

Related

See all

Metadata

Authors
Mac Aodha, O., Gibb, R., Barlow, K. E., Browning, E., Firman, M., Freeman, R., Harder, B., Kinsey, L., Mead, G. R., Newson, S. E., Pandourski, I., Parsons, S., Russ, J., Szodoray-Paradi, A., Szodoray-Paradi, F., Tilova, E., Girolami, M., Brostow, G., & Jones, K. E.
Affiliations
  • University College London (GB)
  • Bat Conservation Trust (GB)
  • Zoological Society of London (GB)
  • British Trust for Ornithology (GB)
  • Bulgarian Academy of Sciences (BG)
  • Queensland University of Technology (AU)
  • Imperial College London (GB)
Corresponding author
Jones, Kate E.
ORCID
Venue
PLOS Computational Biology
Publisher
Public Library of Science (PLoS)
Published
2018-03-08
Volume
14
Issue
3
Pages
e1005995
ISSN
  • 1553-734X (ISSN-L)
  • 1553-7358
DOI
10.1371/journal.pcbi.1005995
PMC
PMC5843167
OpenAlex
W2922355292
Cited by
216
References
64
Citations by year
2026: 22 · 2025: 27 · 2024: 20 · 2023: 26 · 2022: 35 · 2021: 27 · 2020: 25 · 2019: 26 · 2018: 8
FWCI
18.16
Type
journal article
Language
en
Open access
Licence
Locations
  • PLoS Computational Biology (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Edinburgh Research Explorer (University of Edinburgh) (publishedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Figshare (submittedVersion, cc-by)
  • Spiral (Imperial College London) (submittedVersion, cc-by)
Funders
  • Engineering and Physical Sciences Research Council (EP/K015664/1, EP/K503745/1)
  • Natural Environment Research Council (NE/P016677/1)
  • Darwin Initiative (15003, 161333, EIDPR075)
  • Philip Leverhulme Prize
Topics
  • Life Sciences › Agricultural and Biological Sciences › Ecology, Evolution, Behavior and Systematics › Bat Biology and Ecology Studies
  • Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
  • Life Sciences › Agricultural and Biological Sciences › Ecology, Evolution, Behavior and Systematics › Animal Vocal Communication and Behavior
Keywords
bat echolocation calls, convolutional neural networks, passive acoustic monitoring, bat population monitoring, citizen science, Jersey
MeSH terms
Machine Learning, Algorithms, Animals, Chiroptera, Echolocation, Environmental Monitoring, Signal Processing, Computer-Assisted, Zoology, Neural Networks, Computer, Computational Biology, Endangered Species

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review