Skip to content

Research at St Andrews

Automated detection of Hainan gibbon calls for passive acoustic monitoring

Research output: Contribution to journalArticlepeer-review

DOI

Open Access permissions

Open

Author(s)

Emmanuel Dufourq, Ian Durbach, James P. Hansford, Amanda Hoepfner, Heidi Ma, Jessica V. Bryant, Christina S. Stender, Wenyong Li, Zhiwei Liu, Qing Chen, Zhaoli Zhou, Samuel T. Turvey

School/Research organisations

Abstract

Extracting species calls from passive acoustic recordings is a common preliminary step to ecological analysis. For many species, particularly those occupying noisy, acoustically variable habitats, the call extraction process continues to be largely manual, a time-consuming and increasingly unsustainable process. Deep neural networks have been shown to offer excellent performance across a range of acoustic classification applications, but are relatively underused in ecology. We describe the steps involved in developing an automated classifier for a passive acoustic monitoring project, using the identification of calls of the Hainan gibbon Nomascus hainanus, one of the world's rarest mammal species, as a case study. This includes preprocessing-selecting a temporal resolution, windowing and annotation; data augmentation; processing-choosing and fitting appropriate neural network models; and post-processing-linking model predictions to replace, or more likely facilitate, manual labelling. Our best model converted acoustic recordings into spectrogram images on the mel frequency scale, using these to train a convolutional neural network. Model predictions were highly accurate, with per-second false positive and false negative rates of 1.5% and 22.3%. Nearly all false negatives were at the fringes of calls, adjacent to segments where the call was correctly identified, so that very few calls were missed altogether. A post-processing step identifying intervals of repeated calling reduced an 8-h recording to, on average, 22 min for manual processing, and did not miss any calling bouts over 72 h of test recordings. Gibbon calling bouts were detected regularly in multi-month recordings from all selected survey points within Bawangling National Nature Reserve, Hainan. We demonstrate that passive acoustic monitoring incorporating an automated classifier represents an effective tool for remote detection of one of the world's rarest and most threatened species. Our study highlights the viability of using neural networks to automate or greatly assist the manual labelling of data collected by passive acoustic monitoring projects. We emphasize that model development and implementation be informed and guided by ecological objectives, and increase accessibility of these tools with a series of notebooks that allow users to build and deploy their own acoustic classifiers.
Close

Details

Original languageEnglish
JournalRemote Sensing in Ecology and Conservation
VolumeEarly View
Early online date8 Apr 2021
DOIs
Publication statusE-pub ahead of print - 8 Apr 2021

    Research areas

  • Bioacoustics, Convolutional neural networks, Deep learning, Hainan gibbons, Passive acoustic monitoring, Species identification

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by author

  1. Frame-by-frame annotation of video recordings using deep neural networks

    Conway, A., Durbach, I. N., McInnes, A. & Harris, R., Mar 2021, In: Ecosphere. 12, 3, 11 p., e03384.

    Research output: Contribution to journalArticlepeer-review

  2. Fast, flexible alternatives to regular grid designs for spatial capture-recapture

    Durbach, I. N., Borchers, D. L., Sutherland, C. & Sharma, K., Feb 2021, In: Methods in Ecology and Evolution. 12, 2, p. 298-310

    Research output: Contribution to journalArticlepeer-review

  3. Fast and frugal heuristics for portfolio decisions with positive project interactions

    Durbach, I. N., Algorta, S., Kantu, D. K., Katsikopoulos, K. V. & Şimşek, Ö., 1 Nov 2020, In: Decision Support Systems. 138, 12 p., 113399.

    Research output: Contribution to journalArticlepeer-review

  4. Breeding systems of floral colour forms in the Drosera cistiflora species complex

    von Witt, C. G., Anderson, B., Durbach, I. N. & Johnson, S. D., 26 Aug 2020, (E-pub ahead of print) In: Plant Biology. Early View

    Research output: Contribution to journalArticlepeer-review

  5. The Lombard effect in singing humpback whales: source levels increase as ambient ocean noise levels increase

    Guazzo, R. A., Helble, T. A., Alongi, G. C., Durbach, I. N., Martin, C. R., Martin, S. W. & Henderson, E. E., 4 Aug 2020, In: Journal of the Acoustical Society of America. 148, 2, p. 542-555 14 p.

    Research output: Contribution to journalArticlepeer-review

Related by journal

  1. Application of the Random Encounter Model in citizen science projects to monitor animal densities

    Schaus, J., Uzal, A., Gentle, L. K., Baker, P. J., Bearman-Brown, L., Bullion, S., Gazzard, A., Lockwood, H., North, A., Reader, T., Scott, D. M., Sutherland, C. S. & Yarnell, R. W., Dec 2020, In: Remote Sensing in Ecology and Conservation. 6, 4, p. 514-528 15 p.

    Research output: Contribution to journalArticlepeer-review

  2. A roadmap for survey designs in terrestrial acoustic monitoring

    Sugai, L. S. M., Desjonquères, C., Silva, T. S. F. & Llusia, D., Sep 2020, In: Remote Sensing in Ecology and Conservation. 6, 3, p. 220-235 16 p.

    Research output: Contribution to journalReview articlepeer-review

  3. Ultrasonic monitoring to assess the impacts of forest conversion on Solomon Island bats

    Davies, T. E., Ruzicka, F., Lavery, T., Walters, C. L. & Pettorelli, N., Jun 2016, In: Remote Sensing in Ecology and Conservation. 2, 2, p. 107-118

    Research output: Contribution to journalArticlepeer-review

Related by journal

  1. Remote Sensing in Ecology and Conservation (Journal)

    Matt Carter (Reviewer)

    2019

    Activity: Publication peer-review and editorial work typesPeer review of manuscripts

ID: 273733586

Top