EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AVISNet: An edge-computing model for acoustic identification of species from the Doñana bird community

Delia Velasco-Montero iD, David Solís-Martín iD, Jorge Fernández-Berni, Giulia Bastianelli, Javier Bustamante iD

PLOS One · 04.11.2026 · 21 (11) · e0360378

DOI: 10.1371/journal.pone.0360378 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 04.11.2026. Verfasst von Delia Velasco-Montero und 4 weiteren Autor:innen. Beteiligte Einrichtung: Instituto de Microelectronica de Sevilla (IMSE-CNM), Universidad de Sevilla-CSIC, Seville, Spain. Hauptthemen laut MEDLINE: Birds, Acoustics, Vocalization, Animal. Die Arbeit nennt 75 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agencia Estatal de Investigación, European Regional Development Fund, Ministry for Digital Transformation and Civil Service.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The global decline in biodiversity calls for scalable and efficient species monitoring. Birds, as sensitive ecological indicators with rich vocal activity, are particularly well suited for passive acoustic monitoring (PAM), which enables extensive, non-invasive data collection. Yet the large volumes of audio generated by PAM require automated and efficient processing pipelines to extract meaningful biological information in real time. To address this challenge, we integrated automated acoustic species identification directly into embedded devices (i.e., at the edge ), enabling autonomous on-site data processing without reliance on cloud-based computation. Our methodology emphasizes model efficiency and leverages lightweight pre-trained architectures (e.g., MobileNet), alongside advanced learning strategies such as knowledge distillation and few-shot learning to overcome data scarcity for under-represented species. This methodology was applied as a case study to acoustic identification of bird species native to Doñana National Park, Spain. We assessed the performance and efficiency of our models at three levels of acoustic data: focal segments, focal recordings, and soundscape recordings. On focal recordings, our models achieve up to 0.70 F1-score in species identification task. At the soundscape level, we evaluated performance using three real-world soundscape datasets, measuring accuracy metrics at both the vocalization and dataset levels. Our lightweight convolutional neural networks achieve high accuracy at the dataset level (F1-score: 0.56–0.72), solid accuracy at the vocalization level (F1-score: 0.29–0.39; mAP: 0.41-0.69), and fast and energy-efficient inference on resource-limited hardware (2.2–4.7 × speed-ups vs. BirdNET, 41–71% energy savings). Overall, our results show that these networks achieve functional species recognition performance while substantially reducing inference latency and energy requirements relative to BirdNET, thus enabling on-device deployment on low-power units. The system already scales to 300 + species, with room for further expansion, bridging the gap between general-purpose tools like BirdNET and localized embedded monitoring pipelines.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BirdsAcousticsVocalization, AnimalAnimalsSpainBiodiversityNeural Networks, Computer

Autor:innen und Institutionen

  • Instituto de Microelectronica de Sevilla (IMSE-CNM), Universidad de Sevilla-CSIC, Seville, Spain.
  • Universidad de Sevilla, Dpto. Ciencias de la Computación e Inteligencia Artificial, Sevilla, Spain.
  • Estacion Biologica de Doñana (EBD), CSIC, Seville, Spain.
  • ICTS-Doñana, Estacion Biologica de Doñana (EBD), CSIC, Seville, Spain.

ORCID-Profile: Delia Velasco-Montero, David Solís-Martín, Javier Bustamante

Förderung

  • Agencia Estatal de Investigación
  • European Regional Development Fund
  • Ministry for Digital Transformation and Civil Service
  • European Union and Regional Government of Andalucia

Zitieren

APA

Velasco-Montero, D., Solís-Martín, D., Fernández-Berni, J., Bastianelli, G., & Bustamante, J. (2026). AVISNet: An edge-computing model for acoustic identification of species from the Doñana bird community. PLOS One, 21(11), e0360378. https://doi.org/10.1371/journal.pone.0360378

Vancouver

Velasco-Montero D, Solís-Martín D, Fernández-Berni J, Bastianelli G, Bustamante J. AVISNet: An edge-computing model for acoustic identification of species from the Doñana bird community. PLOS One. 2026;21(11):e0360378. doi:10.1371/journal.pone.0360378

BibTeX
@article{VelascoMontero2026,
  author = {Velasco-Montero, Delia and Solís-Martín, David and Fernández-Berni, Jorge and Bastianelli, Giulia and Bustamante, Javier},
  title = {AVISNet: An edge-computing model for acoustic identification of species from the Doñana bird community},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {11},
  pages = {e0360378},
  doi = {10.1371/journal.pone.0360378}
}
Kostenlos starten →