Dataset for "Determining species-specific thresholds to improve precision in passive acoustic monitoring"

Data repository for 10.1016/j.ecoinf.2025.103423 Short Abstract: Automatic and AI-driven species identification is a powerful tool for analysing acoustic data, but its precision varies widely between species, posing a major challenge for reliable monitoring. Species-specific thresholds offer a solution by optimizing model performance for each individual species. Using Alpine birds as a case study and an expert-annotated dataset of 25 hours and 17,737 bird sounds, we provide 72 species-specific thresholds for filtering detections from BirdNET (a widely used sound identification software). The thresholds were calculated with a binomial logistic regression, using BirdNET identification scores as a predictor and the binary annotation (species present or not within the recording) as outcome. Thresholds significantly enhanced precision of the identification model, making them efficient and practical tools for passive acoustic monitoring. This approach could greatly benefit similar monitoring schemes as it could be replicated and applied over different systems and taxa, leading to a significant reduction in time taken to process large amounts of acoustic data.