Large-scale avian vocalization detection delivers reliable global biodiversity insights
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
Tracking biodiversity and its dynamics at scale is essential if we are to solve global environmental challenges. Detecting animal vocalizations in passively recorded audio data offers an automatable, inexpensive, and taxonomically broad way to monitor biodiversity. However, the labor and expertise required to label new data and fine-tune algorithms for each deployment is a major barrier. In this study, we applied a pretrained bird vocalization detection model, BirdNET, to 152,376 h of audio comprising datasets from Norway, Taiwan, Costa Rica, and Brazil. We manually listened to a subset of detections for each species in each dataset, calibrated classification thresholds, and found precisions of over 90% for 109 of 136 species. While some species were reliably detected across multiple datasets, the performance of others was dataset specific. By filtering out unreliable detections, we could extract species and community-level insight into diel (Brazil) and seasonal (Taiwan) temporal scales, as well as landscape (Costa Rica) and national (Norway) spatial scales. Our findings demonstrate that, with relatively fast but essential local calibration, a single vocalization detection model can deliver multifaceted community and species-level insight across highly diverse datasets; unlocking the scale at which acoustic monitoring can deliver immediate applied impact.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Biodiversity loss and its impact on humanity
Cardinale, B. J., Duffy, J. E., Gonzalez, A., Hooper, D. U., Perrings, C., Venail, P., Narwani, A., Mace, G. M., Tilman, D., Wardle, D. A., et al. (2012) · Nature · doi:10.1038/nature11148 · Cited by 7,457
Global Biodiversity: Indicators of Recent Declines
Butchart, S. H. M., Walpole, M., Collen, B., van Strien, A., Scharlemann, J. P. W., Almond, R. E. A., Baillie, J. E. M., Bomhard, B., Brown, C., Bruno, J., et al. (2010) · Science · doi:10.1126/science.1187512 · Cited by 4,892
BirdNET: A deep learning solution for avian diversity monitoring
Kahl, S., Wood, C. M., Eibl, M., & Klinck, H. (2021) · Ecological Informatics · doi:10.1016/j.ecoinf.2021.101236 · Cited by 903
Swanson, A., Kosmala, M., Lintott, C., Simpson, R., Smith, A., & Packer, C. (2015) · Scientific Data · doi:10.1038/sdata.2015.26 · Cited by 510
Computational bioacoustics with deep learning: a review and roadmap
Stowell, D. (2022) · PeerJ · doi:10.7717/peerj.13152 · Cited by 471
BirdNET: applications, performance, pitfalls and future opportunities
Pérez‐Granados, C. (2023) · Ibis · doi:10.1111/ibi.13193 · Cited by 143
Cited by
Ghani, B., Kalkman, V. J., Planqué, B., Vellinga, W.-P., Gill, L., & Stowell, D. (2025) · Scientific Reports · doi:10.1038/s41598-025-00996-2 · Cited by 22
“Calibrating thresholds to local data conditions has been identified to be crucial, if automatic recognition is to produce reliable biodiversity observations 58,59 .”
Yip, D. A., Knight, E. C., & Bayne, E. M. (2026) · Ornithological Applications · doi:10.1093/ornithapp/duaf059 · Cited by 4
Autonomous and Teleoperated Technologies for Comprehensive Rainforest Biodiversity Monitoring
Bonham, D. C., Carpenter, J., Steetz, A., Jung, J., & Spenko, M. (2025) · IEEE Transactions on Field Robotics · doi:10.1109/tfr.2025.3577981 · Cited by 3
Metadata
- Authors
- Sethi, S. S., Bick, A., Chen, M.-Y., Crouzeilles, R., Hillier, B. V., Lawson, J., Lee, C.-Y., Liu, S.-H., de Freitas Parruco, C. H., Rosten, C. M., Somveille, M., Tuanmu, M.-N., & Banks-Leite, C.
- Venue
- Proceedings of the National Academy of Sciences
- Published
- 2024-08-06
- Volume
- 121
- Issue
- 33
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- OpenAlex
- W4401358421
- Cited by
- 50
- References
- 6
- FWCI
- 21.48
- Type
- journal article
- Language
- en
- Open access
- hybrid
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.