BirdNET is as good as experts for acoustic bird monitoring in a European city

BirdNET has become a leading AI for recognising bird species in audio recordings. However, the effect of parameter settings on the algorithm’s performance is not well understood, leaving questions about its applicability in ecological research. We compared the species identification of BirdNET against expert identification using an acoustic dataset consisting of 930 minutes of recordings collected in Munich, Germany. The performance of BirdNET was evaluated using three performance metrics: precision, recall, and F1-score. The metrics were calculated using 24 combinations of the parameters week, sensitivity, and overlap at four temporal aggregations, to also test the effects of recording length. We found that BirdNET closely matched expert identification, particularly when given more data (higher temporal aggregation) and when including the parameters week of the year, a suitable sensitivity, and an overlap of one to two seconds. Thus, our study shows that BirdNET can provide species lists and richness comparable to that of expert ornithologists in acoustic surveys in urban environments. We provide a set of recommendations and parameter settings for BirdNET.