BirdNET: applications, performance, pitfalls and future opportunities
Open accessAbstract
Automated recognition software is paramount for effective passive acoustic monitoring. BirdNET is a free and recently developed bird sound recognizer. I performed a literature review to evaluate the current applications and performance of BirdNET, which is growing in popularity but has been subject to few assessments, and to provide recommendations for future studies using BirdNET. Prior research has employed BirdNET for a wide range of purposes but few studies have linked BirdNET detections to ecological processes or real‐world monitoring schemes. Among evaluated studies, average precision (% detections correctly identified) usually ranged around 72–85%, and recall rate (% target species vocalizations detected) ranged around 33–84%. Some studies did not assess BirdNET performance, which hampers the interpretation of the ecological results and may provide poorly informed decisions. Recommendations on how to evaluate BirdNET efficiency are provided. The impact of the confidence score threshold, a user‐selected parameter as the minimum score for detections reported, on BirdNET output although variable among species is consistent. The use of high confidence score thresholds increases the percentage of detections correctly classified but lowers the proportion of calls and bird species detected. The selection of an optimal score may depend on the priorities of the user and research goals. BirdNET is a great tool for automated bird monitoring but it should be used with caution due to inherent challenges for automated bird identification. The continued refinement of BirdNET suggests further improvements in the coming years.
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.
Integrity signals
Registry
Cites
Statistics
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.
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?
Embeddings derived from large avian recognition systems such as BirdNET, which also form the acoustic feature backbone of pipelines like Perch 2.0, have proven surprisingly general, allowing rapid adaptation of models to new species and environments, including amphibians, bats, and cetaceans.
“Embeddings derived from large avian recognition systems such as BirdNET (Pérez-Granados 2023) which also form the acoustic feature backbone of pipelines like Perch 2.0 (van Merriënboer et al. 2025) have proven surprisingly general, allowing rapid adaptation of models to new species and environments, including amphibians, bats, and cetaceans”
From Listening forward: emerging roles of bioacoustics in ecology, evolution, and conservation (2026) · cites this paper as Pérez-Granados 2023
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
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 · see citing works
Terrestrial Passive Acoustic Monitoring: Review and Perspectives
Sugai, L. S. M., Silva, T. S. F., Ribeiro, J. W., & Llusia, D. (2018) · BioScience · doi:10.1093/biosci/biy147 · Cited by 756 · see citing works
Autonomous recording units in avian ecological research: current use and future applications
Shonfield, J., & Bayne, E. M. (2017) · Avian Conservation and Ecology · doi:10.5751/ace-00974-120114 · Cited by 370 · see citing works
A Comprehensive Overview of Technologies for Species and Habitat Monitoring and Conservation
Lahoz‐Monfort, J. J., & Magrath, M. J. L. (2021) · BioScience · doi:10.1093/biosci/biab073 · Cited by 321 · see citing works
Pérez‐Granados, C., & Traba, J. (2021) · Ibis · doi:10.1111/ibi.12944 · Cited by 231 · see citing works
Self-citationKnight, E. C., Hannah, K. C., Foley, G. J., Scott, C. D., Brigham, R. M., & Bayne, E. M. (2017) · Avian Conservation and Ecology · doi:10.5751/ace-01114-120214 · Cited by 230 · see citing works
Darras, K., Batáry, P., Furnas, B. J., Celis‐Murillo, A., Wilgenburg, S. L. V., Mulyani, Y. A., & Tscharntke, T. (2018) · Journal of Applied Ecology · doi:10.1111/1365-2664.13229 · Cited by 195 · see citing works
Comparison of audio recording system performance for detecting and monitoring songbirds
Rempel, R. S., Francis, C. M., Robinson, J. N., & Campbell, M. (2013) · Journal of Field Ornithology · doi:10.1111/jofo.12008 · Cited by 93 · see citing works
Wood, C. M., Kahl, S., Chaon, P., Peery, M. Z., & Klinck, H. (2021) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13571 · Cited by 83 · see citing works
Wood, C. M., Kahl, S., Rahaman, A., & Klinck, H. (2022) · PLoS Biology · doi:10.1371/journal.pbio.3001670 · Cited by 76 · see citing works
Cole, J. S., Michel, N. L., Emerson, S. A., & Siegel, R. B. (2022) · Ornithological Applications · doi:10.1093/ornithapp/duac003 · Cited by 71 · see citing works
Pérez‐Granados, C., & Schuchmann, K. (2020) · Journal für Ornithologie · doi:10.1007/s10336-020-01795-4 · Cited by 61 · see citing works
Self-citationManzano‐Rubio, R., Bota, G., Brotons, L., Soto-Largo, E., & Pérez‐Granados, C. (2022) · Ecological Informatics · doi:10.1016/j.ecoinf.2022.101910 · Cited by 61 · see citing works
Self-citationPérez‐Granados, C., Bota, G., Giralt, D., Albarracín, J., & Traba, J. (2019) · Ardeola · doi:10.13157/arla.66.2.2019.ra4 · Cited by 48 · see citing works
Self-citationAdvancing bird survey efforts through novel recorder technology and automated species identification
Toenies, M., & Rich, L. N. (2021) · California Fish and Wildlife Journal · doi:10.51492/cfwj.107.5 · Cited by 47 · see citing works
Bio-acoustic tracking and localization using heterogeneous, scalable microphone arrays
Verreycken, E., Simon, R., Quirk-Royal, B., Daems, W., Barber, J. R., & Steckel, J. (2021) · Communications Biology · doi:10.1038/s42003-021-02746-2 · Cited by 44 · see citing works
Bird@Edge: Bird Species Recognition at the Edge
Höchst, J., Bellafkir, H., Lampe, P., Vogelbacher, M., Mühling, M., Schneider, D. M., Lindner, K., Rösner, S., Schabo, D. G., Farwig, N., et al. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17436-0_6 · Cited by 34 · see citing works
Distance truncation via sound level for bioacoustic surveys in patchy habitat
Hedley, R. W., Wilson, S. J., Yip, D. A., Li, K., & Bayne, E. M. (2020) · Bioacoustics · doi:10.1080/09524622.2020.1730240 · Cited by 17 · see citing works
Ornithology meets the IoT: Automatic Bird Identification, Census, and Localization
Brüggemann, L., Schütz, B., & Aschenbruck, N. (2021) · IEEE World Forum on Internet of Things (WF-IoT) · doi:10.1109/wf-iot51360.2021.9595401 · Cited by 17 · see citing works
Identifying Birds by Sound: Large-scale Acoustic Event Recognition for Avian Activity Monitoring
Kahl, M. (2020) · Cited by 13 · see citing works
Testing the Accuracy of a birdNET, Automatic bird song Classifier
Arif, M., Hedley, R. W., & Bayne, E. M. (2020) · ERA: Education and Research Archive (University of Alberta) · doi:10.7939/r3-6khb-kz18 · Cited by 10 · see citing works
Bolcar, M. (2020) · Maryland Shared Open Access Repository (USMAI Consortium) · doi:10.13016/m2iviu-44e1 · Cited by 1 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- Malamut, E.J. 2022. Using autonomous recording units and image processing to investigate patterns in avian singing activity and nesting phenology . Doctoral dissertation, University of California, Los Angeles.
- Tolkova, I., Chu, B., Hedman, M., Kahl, S. & Klinck, H. 2021. Parsing birdsong with deep audio Embeddings. arXiv preprint arXiv:2108.09203 . · arXiv
Cited by
Sorted by citations
Listening forward: emerging roles of bioacoustics in ecology, evolution, and conservation
Zsebők, S. (2026) · Biologia Futura · doi:10.1007/s42977-026-00322-5
“Embeddings derived from large avian recognition systems such as Bird-NET (Pérez-Granados 2023) which also form the acoustic feature backbone of pipelines like Perch 2.0 (van Merriën-boer et al. 2025) have proven surprisingly general, allowing rapid adaptation of models to new species and…”
Influential
- Authors
- Pérez‐Granados, C.
- Affiliations
- University of Alicante (ES)
- Corresponding author
- Pérez‐Granados, Cristian
- Venue
- Ibis
- Publisher
- Wiley
- Published
- 2023-02-27
- Volume
- 165
- Issue
- 3
- Pages
- 1068-1075
- ISSN
- 0019-1019 (ISSN-L)
- 1474-919X
- OpenAlex
- W4322630137
- Cited by
- 143
- References
- 22
- Citations by year
- 2026: 45 · 2025: 58 · 2024: 30 · 2023: 10
- FWCI
- 35.19
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Ibis (publishedVersion, cc-by-nc)
- Repositori ObertUDL (University of Lleida) (submittedVersion, cc-by)
- RUA, Repositorio Institucional de la Universidad de Alicante (Universidad de Alicante) (submittedVersion, cc-by-nc)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Developmental Biology › Animal Vocal Communication and Behavior
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Physical Sciences › Environmental Science › Ecology › Avian ecology and behavior
- Keywords
- BirdNET, passive acoustic monitoring, detection accuracy, species identification
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
