Towards automated detection of the endangered southern black-throated finch (Poephila cincta cincta)

Slade Allen-Ankins; Juan Mula Laguna; Lin Schwarzkopf

doi:10.1071/WR23151

RESEARCH ARTICLE (Open Access)

Previous Next Contents Vol 51(10)

Towards automated detection of the endangered southern black-throated finch (Poephila cincta cincta)

Slade Allen-Ankins

^A ^* , Juan Mula Laguna ^A and Lin Schwarzkopf ^A

+ Author Affiliations

- Author Affiliations

^A College of Science and Engineering, James Cook University, Townsville, Qld, Australia.

^* Correspondence to: slade.allenankins@jcu.edu.au

Handling Editor: Shannon Dundas

Wildlife Research 51, WR23151 https://doi.org/10.1071/WR23151

Submitted: 28 November 2023 Accepted: 17 August 2024 Published: 30 September 2024

© 2024 The Author(s) (or their employer(s)). Published by CSIRO Publishing. This is an open access article distributed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND)

Abstract

Context

Biodiversity is declining worldwide, with many species decreasing in both number and range. Acoustic monitoring is rapidly becoming a common survey method in the ecologist’s toolkit that may aid in the conservation of endangered species, but effective analysis of long-duration audio recordings is still challenging.

Aims

The aims of this study were to: (1) develop and test call recognisers for the endangered southern black-throated finch (Poephila cincta cincta) as well as the similar sounding, but non-endangered, double-barred finch (Taeniopygia bichenovii); and (2) compare the ability of these recognisers to detect these species with that of on-ground bird surveys at under-surveyed locations in the Desert Uplands bioregion which is at the edge of the known range of the black-throated finch.

Methods

A range of convolutional neural network call recognition models were built and tested for both target species, before being deployed over new audio recordings collected at 25 sites during 2020, 2021 and 2022, and compared with the results of on-ground bird surveys at those same sites.

Key results

Call recognisers for both species performed well on test datasets from locations in the same area as the training data with an average area under the precision-recall curve (PRAUC) of 0.82 for black-throated finch and 0.87 for double-barred finch. On-ground bird surveys in the Desert Uplands bioregion detected black-throated finches at two locations in different years, and our call recognisers confirmed this with minimal post-validation of detections. Similar agreement between methods were obtained for the double-barred finch, with site occupancy in the Desert Uplands bioregion confirmed with audio recognition in all nine surveys with on-ground detections, as well as during four additional surveys that had no on-ground detections.

Conclusions

Using call recognisers to survey new locations for black-throated finch presence was equally successful as on-ground surveys, and with further refinements, such as retraining models with examples of commonly misclassified vocalisations added to the training data, minimal validation should be required to detect site presence.

Implications

Acoustic monitoring should be considered as a valuable tool to be used alongside manual surveys to allow effective monitoring and conservation of this endangered species.

Keywords: acoustic monitoring, black-throated finch, call recogniser, conservation, convolutional neural network, double-barred finch, machine learning, threatened species.

References

Allaire JJ, Chollet F (2020) Keras: R interface to ‘keras’. Available at https://CRAN.R-project.org/package=keras

Allaire JJ, Tang Y (2020) Tensorflow: R interface to ‘tensorflow’. Available at https://CRAN.R-project.org/package=tensorflow

Barnosky AD, Matzke N, Tomiya S, Wogan GOU, Swartz B, Quental TB, Marshall C, McGuire JL, Lindsey EL, Maguire KC, Mersey B, Ferrer EA (2011) Has the Earth’s sixth mass extinction already arrived? Nature 471, 51-57.
| Crossref | Google Scholar | PubMed |

Buda M, Maki A, Mazurowski MA (2018) A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks 106, 249-259.
| Crossref | Google Scholar | PubMed |

Ceballos G, Ehrlich PR, Raven PH (2020) Vertebrates on the brink as indicators of biological annihilation and the sixth mass extinction. Proceedings of the National Academy of Sciences 117, 13596-13602.
| Crossref | Google Scholar |

Crump PS, Houlahan J (2017) Designing better frog call recognition models. Ecology and Evolution 7, 3087-3099.
| Crossref | Google Scholar | PubMed |

Darras K, Batáry P, Furnas BJ, Grass I, Mulyani YA, Tscharntke T (2019) Autonomous sound recording outperforms human observation for sampling birds: a systematic map and user guide. Ecological Applications 29, e01954.
| Crossref | Google Scholar | PubMed |

Digby A, Towsey M, Bell BD, Teal PD (2013) A practical comparison of manual and autonomous methods for acoustic monitoring. Methods in Ecology and Evolution 4, 675-683.
| Crossref | Google Scholar |

Efremova DB, Sankupellay M, Konovalov DA (2019) Data-efficient classification of birdcall through convolutional neural networks transfer learning. In ‘2019 Digital Image Computing: Techniques and Applications (DICTA)’, pp. 1–8. (IEEE)

Eichinski P, Alexander C, Roe P, Parsons S, Fuller S (2022) A convolutional neural network bird species recognizer built from little data by iteratively training, detecting, and labeling. Frontiers in Ecology and Evolution 10, 810330.
| Crossref | Google Scholar |

Gaston KJ, Rodrigues ASL (2003) Reserve selection in regions with poor biological data. Conservation Biology 17, 188-195.
| Crossref | Google Scholar |

Gibb R, Browning E, Glover-Kapfer P, Jones KE (2019) Emerging opportunities and challenges for passive acoustics in ecological assessment and monitoring. Methods in Ecology and Evolution 10, 169-185.
| Crossref | Google Scholar |

Grand J, Cummings MP, Rebelo TG, Ricketts TH, Neel MC (2007) Biased data reduce efficiency and effectiveness of conservation reserve networks. Ecology Letters 10, 364-374.
| Crossref | Google Scholar | PubMed |

He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In ‘Proceedings of the IEEE conference on computer vision and pattern recognition’, pp. 770–778. (IEEE, 2016)

Incze A, Jancsó H-B, Szilágyi Z, Farkas A, Sulyok C (2018) Bird sound recognition using a convolutional neural network. In ‘2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY)’, pp. 000295–000300. (IEEE)

Kahl S, Wood CM, Eibl M, Klinck H (2021) BirdNET: a deep learning solution for avian diversity monitoring. Ecological Informatics 61, 101236.
| Crossref | Google Scholar |

Lasseck M (2019) Bird species identification in soundscapes. CLEF (Working Notes) 2380,.
| Google Scholar |

Lauha P, Somervuo P, Lehikoinen P, Geres L, Richter T, Seibold S, Ovaskainen O (2022) Domain-specific neural networks improve automated bird sound recognition already with small amount of local data. Methods in Ecology and Evolution 13, 2799-2810.
| Crossref | Google Scholar |

Lemen C, Freeman PW, White JA, Andersen BR (2015) The problem of low agreement among automated identification programs for acoustical surveys of bats. Western North American Naturalist 75, 218-225.
| Crossref | Google Scholar |

Lewy D, Mańdziuk J (2023) An overview of mixing augmentation methods and augmentation strategies. Artificial Intelligence Review 56, 2111-2169.
| Crossref | Google Scholar |

Mula Laguna J (2020) Understanding uncertainty to inform conservation: Tools to protect the endangered black-throated finch southern subspecies. PhD Thesis, James Cook University.

Mula Laguna J, Reside AE, Kutt A, Grice AC, Buosi P, Vanderduys EP, Taylor M, Schwarzkopf L (2019) Conserving the endangered black-throated finch southern subspecies: what do we need to know? Emu - Austral Ornithology 119, 331-345.
| Crossref | Google Scholar |

Pérez-Granados C, Traba J (2021) Estimating bird density using passive acoustic monitoring: a review of methods and suggestions for further research. Ibis 163, 765-783.
| Crossref | Google Scholar |

Priyadarshani N, Marsland S, Castro I (2018) Automated birdsong recognition in complex acoustic environments: a review. Journal of Avian Biology 49, jav-01447.
| Crossref | Google Scholar |

R Core Team (2019) ‘R: a language and environment for statistical computing.’ (R Core Team)

Rechetelo J, Grice A, Reside AE, Hardesty BD, Moloney J (2016) Movement patterns, home range size and habitat selection of an endangered resource tracking species, the black-throated finch (Poephila cincta cincta). PLoS ONE 11, e0167254.
| Crossref | Google Scholar | PubMed |

Reside AE, Cosgrove AJ, Pointon R, Trezise J, Watson JEM, Maron M (2019) How to send a finch extinct. Environmental Science & Policy 94, 163-173.
| Crossref | Google Scholar |

Rocha LHS, Ferreira LS, Paula BC, Rodrigues FHG, Sousa-Lima RS (2015) An evaluation of manual and automated methods for detecting sounds of maned wolves (Chrysocyon brachyurus illiger 1815). Bioacoustics 24, 185-198.
| Crossref | Google Scholar |

Ruff ZJ, Lesmeister DB, Duchac LS, Padmaraju BK, Sullivan CM (2020) Automated identification of avian vocalizations with deep convolutional neural networks. Remote Sensing in Ecology and Conservation 6, 79-92.
| Crossref | Google Scholar |

Schroeder KM, McRae SB (2020) Automated auditory detection of a rare, secretive marsh bird with infrequent and acoustically indistinct vocalizations. Ibis 162, 1033-1046.
| Crossref | Google Scholar |

Schwarzkopf L, Roe P, Mcdonald PG, Watson DM, Fuller RA, Allen-Ankins S (2023) Can an acoustic observatory contribute to the conservation of threatened species? Austral Ecology 48, 1230-1237.
| Crossref | Google Scholar |

Stowell D, Wood MD, Pamuła H, Stylianou Y, Glotin H (2019) Automatic acoustic detection of birds through deep learning: the first bird audio detection challenge. Methods in Ecology and Evolution 10, 368-380.
| Crossref | Google Scholar |

Sueur J, Aubin T, Simonis C (2008) Seewave, a free modular tool for sound analysis and synthesis. Bioacoustics 18, 213-226.
| Crossref | Google Scholar |

Sugai LSM, Silva TSF, Ribeiro JW, Jr, Llusia D (2019) Terrestrial passive acoustic monitoring: review and perspectives. BioScience 69, 15-25.
| Crossref | Google Scholar |

Sugai LSM, Desjonquères C, Silva TSF, Llusia D (2020) A roadmap for survey designs in terrestrial acoustic monitoring. Remote Sensing in Ecology and Conservation 6, 220-235.
| Crossref | Google Scholar |

Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In ‘Proceedings of the IEEE conference on computer vision and pattern recognition’. pp. 2818–2826.

Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In ‘Proceedings of the AAAI conference on artificial intelligence’. pp. 4278–4284. (AAAI)

Teixeira D, Linke S, Hill R, Maron M, van Rensburg BJ (2022) Fledge or fail: nest monitoring of endangered black-cockatoos using bioacoustics and open-source call recognition. Ecological Informatics 69, 101656.
| Crossref | Google Scholar |

Vanderduys EP, Reside AE, Grice A, Rechetelo J (2016) Addressing potential cumulative impacts of development on threatened species: the case of the endangered black-throated finch. PLoS ONE 11, e0148485.
| Crossref | Google Scholar | PubMed |

Venier LA, Holmes SB, Holborn GW, Mcilwrick KA, Brown G (2012) Evaluation of an automated recording device for monitoring forest birds. Wildlife Society Bulletin 36, 30-39.
| Crossref | Google Scholar |

Waddle JH, Thigpen TF, Glorioso BM (2009) Efficacy of automatic vocalization recognition software for anuran monitoring. Herpetological Conservation and Biology 4, 384-388.
| Google Scholar |