National-scale acoustic monitoring of avian biodiversity and phenology

Abstract Billions of birds migrate annually, triggered by endogenous behaviors as well as ecoclimatic triggers, which are shifting with climate change. These dynamics play out over large spatiotemporal scales, making monitoring of phenology challenging with traditional biodiversity survey approaches. In this study, over a complete spring season, we collected 37,429 hours of audio from 28 networked sensors in forests across Norway. We used machine learning to automatically identify bird vocalizations, and with expert validation found we were able to classify 57 species (14 full migrants) with over 80% precision. We show that acoustic surveys can fill data gaps in traditional surveys and facilitate mapping of migratory waves across Norwegian forests. Our study demonstrates how acoustic monitoring can complement existing national-scale biodiversity datasets, delivering high quality data which can support the design and implementation of effective policy and conservation measures.