Work

Listening to the city: evaluating BirdNET reliability and bias in urban bird community assessments

Year: 2026

Type: dataset

Abstract: This archive contains the datasets and R scripts supporting the article "Listening to the city: evaluating BirdNET reliability and bias in urban bird community assessments" by Ferrario V., Alba R., Marcolin F., Brambilla G., Chamberlain D. and Caprio E., accepted in Remote Sensing in Ecology and Conservation.Passive acoustic recordings were collected with AudioMoth recorders in urban green areas of Turin (28 May to 6 June 2024) and Florence (6 to 13 May 2024), Italy, and analysed with BirdNET Analyzer using a minimum confidence of 0.3. For each species detected, up to 500 three-second segments per city were manually validated as correct or incorrect. Incorrect segments were assigned to a sound category (biophony, anthropophony or geophony).

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.23106210

Authors: Ferrario, Valeria, Alba, Riccardo, Marcolin, Fabio, Brambilla, Giordano, Chamberlain, Dan, Caprio, Enrico

Institution: University of Turin

Language: English

Topic: Animal Vocal Communication and Behavior

Subfield: Ecology, Evolution, Behavior and Systematics

Field: Agricultural and Biological Sciences

Domain: Life Sciences

SDG: Sustainable cities and communities

Open Access status: green

OpenAlex ID: W7216112461

Cites:

Cited by:

Related to: 10