An automated workflow that combines sound‐based bird identification and localization

Field studies of bird communities typically require the fine‐scale mapping of individuals. Passive acoustic monitoring combined with localization of individuals is a promising approach to gather such data. Various approaches for the identification of species and localization of individuals have been proposed, but there is so far no fully automated ready‐to‐use workflow that combines identification and localization. We here present a novel approach based on sound recordings with multiple cost‐efficient autonomous recording units (Audiomoths). The workflow uses a well‐established artificial intelligence model (BirdNET; other models possible) for species identification and localizes the sources of all identified bird sounds with high accuracy. Tests with replayed sounds of different bird species in an agricultural landscape show that – after filtering out identifications with low identification confidence – the algorithm localizes more than 92% of the sounds within 2 m of the true location (78% <1 m). We used the workflow to localize wild birds, to demonstrate its applicability in a real‐world situation and its usefulness for avian ecology. This workflow is completely automated and ready‐to‐be‐used, including by non‐experts. It can also be used when strong winds affect the speed of sound or if three‐dimensional localizations are of interest. By making data on individual bird locations accessible, the presented work will help to advance fundamental and applied ecology as well as conservation.