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.

BirdNET is a popular machine learning tool for automated recognition of bird sounds. Here we evaluate how BirdNET settings affect the model performance both at vocalization and species levels, using 4,225 one-minute 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 vocalisations, whereas higher thresholds (around 0.5) are more suitable for characterising bird communities. Based on our findings, we recommend increasing the Overlap parameter from its default value of 0 seconds to 2 seconds, as this consistently improves BirdNET performance in detecting both individual vocalisations and species presence. The effect of the Sensitivity parameter varied across regions. However, a value of 0.5 maximises global performance for community-level analyses across all confidence thresholds, while a value of 1.5 generally yields better results for vocalisation-level studies, particularly at low confidence thresholds.

Mounting evidence points to widespread declines in insect abundance and diversity across European terrestrial ecosystems, highlighting an urgent need for effective large-scale monitoring methods. Passive acoustic monitoring enables the monitoring of sound-producing insects at an unprecedented temporal and spatial scale by remotely capturing sounds such as orthopteran stridulations and cicada timbalizations. However, current automated recognition tools for European insect sounds remain limited, and developing algorithms capable of reliably identifying diverse species requires large, ecologically heterogeneous acoustic datasets. Here we present a dataset of 11,224 recordings covering 193 orthopteran and 24 cicada species from North, Central, and temperate Western Europe. It combines coarsely labeled recordings, for which we can only infer the presence, at some point, of their target species (weak labeling), with finely annotated recordings that specify the time and frequency range of each insect sound (strong labeling). This dataset complements existing online resources and supports the advancement of automated acoustic classification for orthopterans and cicadas, aiding biodiversity monitoring efforts across Europe.

Passive acoustic monitoring has become increasingly popular as a practical and cost-effective way of obtaining highly reliable acoustic data in ecological research projects. Increased ease of collecting these data means that, currently, the main bottleneck in ecoacoustic monitoring projects is often the time required for the manual analysis of passively collected recordings. In this study we evaluate the potential and current limitations of BirdNET-Analyzer v2.4, the most advanced and generic deep learning algorithm for bird recognition to date, as a tool to assess bird community composition through the automated analysis of large-scale ecoacoustic data. To this end, we study 3 acoustic datasets comprising a total of 629 environmental soundscapes collected in 194 different sites spread across a 19° latitude span in Europe. We analyze these recordings both with BirdNET and by manual listening by local expert birders, and we then compare the results obtained through the two methods to evaluate the performance of the algorithm both at the level of each single vocalization and for entire recording sequences (1, 5 or 10 min). Our analyses reveal that BirdNET identifications can be highly reliable if a sufficiently high minimum confidence threshold is used. However, the current recall of the algorithm is markedly low when the minimum confidence threshold is adjusted to ensure high levels of precision. Thus, we found that F1-scores remain moderate (<0.5) for all datasets and confidence thresholds studied. We therefore estimate that acoustic datasets of extended duration are currently necessary for BirdNET to provide a reliable and minimally comprehensive picture of the target bird community. Our results also suggest that BirdNET performance is not significantly influenced by the type of recorder used or the habitat recorded but is modulated by the volume of species-specific acoustic data available online. We conclude that a judicious use of AI-based IDs provided by BirdNET can represent a novel and powerful method to assist in the assessment of bird community composition through the automated analysis of large-scale ecoacoustic data. Finally, we provide best use recommendations to ensure optimal results from the algorithm for the ecological study of bird communities.