EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Optimization of passive acoustic bird surveys: a global assessment of BirdNET settings

Cristian Pérez‐Granados, David Funosas, Jon Morant, Oscar H. Marín Gómez, Irene Mendoza, Miguel A. Mohedano‐Munoz, Eduardo Santamaría, Giulia Bastianelli, Alba Márquez‐Rodríguez, Michał Budka, Gerard Bota, José M. De la Peña‐Rubio und 28 weitere

Ibis · 2026-04 · 168 (2) · 785-798

DOI: 10.1111/ibi.70013 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Ibis, online erschienen am 24.11.2025. Verfasst von Cristian Pérez‐Granados und 39 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BirdNET is a popular machine learning tool for automated recognition of bird sounds. However, evidence on how to optimize its settings for accurate bird monitoring remains limited. Here, we evaluate how BirdNET settings influence model performance in identifying bird vocalizations and characterizing bird communities, using 4224 1‐min recordings from 67 recording locations worldwide. Giving equal importance to recall and precision, a low confidence score threshold (0.1–0.3) appears optimal for detecting bird vocalizations, whereas higher thresholds (around 0.5) are more suitable for characterizing bird communities. Based on our findings, we recommend increasing the Overlap parameter from its default value of 0 to 2 s, as this consistently improves BirdNET performance in detecting both bird vocalizations and species presence. The effect of the Sensitivity parameter varied across regions. However, a value of 0.5 maximizes global performance for community‐level analyses across all confidence thresholds, and a value of 1.5 generally yields better results for vocalization‐level studies, particularly at low confidence thresholds. Our findings offer practical guidance for selecting BirdNET settings in passive acoustic bird surveys, enhancing both the identification of bird vocalizations and the characterization of bird communities.

Zitieren

APA

Pérez‐Granados, C., Funosas, D., Morant, J., Gómez, O. H. M., Mendoza, I., Mohedano‐Munoz, M. A., Santamaría, E., Bastianelli, G., Márquez‐Rodríguez, A., Budka, M., Bota, G., Peña‐Rubio, J. M. D. L., Morena, E. G. D. L., Santa‐Cruz, M., Nava, P. D. L., Fernández‐Tizón, M., Sánchez‐Mateos, H., Barrero, A., Traba, J., …, & Müeller, S. (2026). Optimization of passive acoustic bird surveys: a global assessment of BirdNET settings. Ibis, 168(2), 785-798. https://doi.org/10.1111/ibi.70013

Vancouver

Pérez‐Granados C, Funosas D, Morant J, Gómez OHM, Mendoza I, Mohedano‐Munoz MA, et al. Optimization of passive acoustic bird surveys: a global assessment of BirdNET settings. Ibis. 2026;168(2):785-798. doi:10.1111/ibi.70013

BibTeX
@article{PrezGranados2026,
  author = {Pérez‐Granados, Cristian and Funosas, David and Morant, Jon and Gómez, Oscar H. Marín and Mendoza, Irene and Mohedano‐Munoz, Miguel A. and Santamaría, Eduardo and Bastianelli, Giulia and Márquez‐Rodríguez, Alba and Budka, Michał and Bota, Gerard and Peña‐Rubio, José M. De la and Morena, Eladio García De La and Santa‐Cruz, Manu and Nava, Pablo De la and Fernández‐Tizón, Mario and Sánchez‐Mateos, Hugo and Barrero, Adrián and Traba, Juan and Osiejuk, Tomasz S. and Hart, Patrick J. and Navine, Amanda K. and Muñoz, Andrés F. Montoya and Araújo, Carlos B. De and Rosa, Gabriel L. M. and Torres, Ingrid M. D. and Catalano, Ana L. C. and Simões, Cassio Rachid and Llusia, Diego and Morales, Manuel B. and Acebes, Pablo and Medina, Juan A. and Brown, Nicholas and Astaras, Christos and Karmiris, Ilias and Navarrete, Elizabeth and Cauchoix, Maxime and Barbaro, Luc and Arend, Dominik and Müeller, Sandra},
  title = {Optimization of passive acoustic bird surveys: a global assessment of BirdNET settings},
  journal = {Ibis},
  year = {2026},
  volume = {168},
  number = {2},
  pages = {785--798},
  doi = {10.1111/ibi.70013}
}
Kostenlos starten →