Skip to main content

Biodiversity monitoring using new technologies

RYC2024-048830-I

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de Recursos Humanos
Subprogram Subprograma Estatal de Formación, Atracción y Retención del Talento Investigador e Innovador
Call Ramón y Cajal
Call year 2024
State Plan 2024-2027 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre CONSORCI CENTRE DE CIÈNCIA I TECNOLOGIA FORESTAL DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

RUA. Repositorio Institucional de la Universidad de Alicante
Publication Otros (Other)

Global assessment of spatial and temporal filters on BirdNET performance for monitoring bird communities

  • Pérez-Granados, Cristian
  • Morant, Jon
  • Funosas, David
  • Sebastián-González, Esther
  • Morant, Jon|||/items/f5c63ce0-a69a-483c-b591-c2e7b22a83f8
  • Sebastián-González, Esther|||/items/c53fd431-7978-4887-bee5-296d259dab12
Recent advances in automated technologies, such as passive acoustic monitoring, provide a powerful framework for surveying bird communities at broad spatial scales. Among the most widely used artificial intelligence tools for automated bird sound recognition is BirdNET, which can identify over 6,000 species worldwide. However, the effects of key user-defined settings, such as species filtering, remain poorly evaluated. Here, we assess how alternative species-filtering strategies influence BirdNET performance in describing bird communities worldwide. We analysed 5,047 min of sound recordings from 72 locations worldwide, comprising 1,192 bird species identified by expert ornithologists. We compared three common species-filtering approaches applied in BirdNET workflows to post-process its output: no filtering, spatial filtering (species present all-year at a given location), and spatio-temporal filtering (species present at a given location and week). The unfiltered approach maximized BirdNET species detection (recall) but suffered very low precision (had many misidentifications) and poor overall performance. In contrast, the other two filtering strategies greatly improved precision and overall performance, despite moderate reductions in recall. Among them, spatio-temporal filtering consistently achieved the best performance across most datasets and regions globally. Within this optimal filtering approach, we also evaluated the role of another parameter: occurrence probability thresholds. Intermediate values of this threshold (around 0.05) maximized BirdNET performance in community-level analyses. Our results demonstrate that species filtering is a key but often underappreciated component of BirdNET workflows. We hope our findings may guide future studies in selecting optimal species filters, while emphasising that filtering selection should be guided by study objectives and data context.
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publication Artículo científico (JournalArticle)

A large-scale acoustic dataset of a passerine with spatially variable vocal behavior: fine-scale annotations of song and call types

  • Pérez-Granados, Cristian
  • Alonso-Moya, Cristina D.
  • Barrero, Adrián
  • Sáez-Gómez, Pedro
  • Bota, Gerard
  • Lahoz-Monfort, José J.
  • Osiejuk, Tomasz S.
  • Rogers, Alex
  • Schuchmann, Karl-L.
  • Traba, Juan
The study of bird vocal behavior provides insights into ecology, evolution, and conservation. Prior research has mostly focused on bird songs, with limited attention to calling behavior. Although the origins and functions of these vocalizations differ, no detailed annotated acoustic datasets are currently available including both bird songs and calls. Here, we present an acoustic dataset with standardized recordings and detailed annotations of singing and calling behavior in the Dupont’s lark (Chersophilus duponti), a passerine with spatially variable vocal behavior. Recordings were collected across a large spatial scale (20 populations) to capture geographic variation in vocalizations. The dataset includes 4,297 annotated songs from 191 singing males, representing 401 song types, and 795 annotated calls from 97 calling males, representing 80 call types. Annotations provide precise categorization of song and call types, enabling comparisons of individual and population vocal repertoires, geographic variation, and potential effects of habitat fragmentation on vocal behavior. This dataset is intended for reuse in studies of bird vocal behavior, comparative analyses of song and call patterns, and research on passerine acoustic communication., The results are part of project PID2022-139294NB-I00, funded by the Ministerio de Ciencia e Innovación of Spain (MCIN/AEI/10.13039/501100011033/FEDER/UE). CPG was funded by the Ramón y Cajal 2024 Programme (RYC2024-048830-I) of the Spanish Ministry of Science, Innovation and Universities, funded by MICIU/AEI/10.13039/501100011033 and FSE+., Peer reviewed