Acoustic individual identification in a species of field cricket using deep learning
The Journal of the Acoustical Society of America · 01.06.2026 · 159 (6) · 5288-5299
DOI: 10.1121/10.0044100 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 15.06.2026. Verfasst von Emmanuel Kabuga und 6 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Statistics in Ecology, the Environment, and Conservation, University of Cape Town, South Africa. Hauptthemen laut MEDLINE: Gryllidae, Deep Learning, Vocalization, Animal, Acoustics. Die Arbeit nennt 54 Literaturangaben.
Abstract (Originalsprache)
Individual animal identification is essential for wildlife conservation and management, aiding in estimating abundance and related parameters. The feasibility of identifying individual field crickets (Plebeiogryllus guttiventris) from their calls using deep learning is assessed. In a closed population, the best models recognized individuals with up to 99.9% accuracy when trained and tested on calls from the same night, and 65.1% accuracy when tested on calls from nights not used in training. When matching call pairs without knowing all individuals in the population, models identified pairs of calls from the same night with 97.4% accuracy, falling to 87.8% if calls were from different nights. Accuracy remained high when tested on individuals not observed during training (within night, 95.0%; across nights, 82.7%). Pooling training data from multiple nights improved test accuracy for all models. Deep learning outperformed random forests, especially on harder tasks, although both were able to discriminate individuals. Higher temperatures were associated with shorter chirps and higher frequencies, but adjusting spectrograms for these traits did not improve performance. These results provide the demonstration of acoustic individual identification (AIID), using wild recordings of an insect species, and highlight the potential of deep learning-based AIID for noninvasive animal population monitoring.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Centre for Statistics in Ecology, the Environment, and Conservation, University of Cape Town, South Africa.
- African Institute for Mathematical Sciences (AIMS South Africa), Cape Town, South Africa.
- School of Arts and Sciences, Azim Premji University, Bangalore, India.
- Centre for Research into Ecological and Environmental Modelling, University of Saint Andrews, United Kingdom.
- Centre for Ecological Sciences, Indian Institute of Science, Bangalore, India.
- Medical Research Council Unit The Gambia at London School of Hygiene and Tropical Medicine, The Gambia.
ORCID-Profile: Emmanuel Kabuga, Diptarup Nandi, Stuart Burrell, Bubacarr Bah, Ian Durbach
Zitieren
APA
Kabuga, E., Nandi, D., Burrell, S., Dlamini, G., Balakrishnan, R., Bah, B., & Durbach, I. (2026). Acoustic individual identification in a species of field cricket using deep learning. The Journal of the Acoustical Society of America, 159(6), 5288-5299. https://doi.org/10.1121/10.0044100
Vancouver
Kabuga E, Nandi D, Burrell S, Dlamini G, Balakrishnan R, Bah B, et al. Acoustic individual identification in a species of field cricket using deep learning. The Journal of the Acoustical Society of America. 2026;159(6):5288-5299. doi:10.1121/10.0044100
BibTeX
@article{Kabuga2026,
author = {Kabuga, Emmanuel and Nandi, Diptarup and Burrell, Stuart and Dlamini, Gciniwe and Balakrishnan, Rohini and Bah, Bubacarr and Durbach, Ian},
title = {Acoustic individual identification in a species of field cricket using deep learning},
journal = {The Journal of the Acoustical Society of America},
year = {2026},
volume = {159},
number = {6},
pages = {5288--5299},
doi = {10.1121/10.0044100}
}
EUVIMED