Understanding how species adjust to seasonality is fundamental in ecology, especially with rapidly increasing global air temperatures. Bioacoustic monitoring offers promise for tracking shifts in seasonal timing of vocal species, as recent automated sound recorders enable large-scale and long-term data collection. Yet, analyzing vast datasets necessitates automation and innovative detection methods. Here, we introduce BioSoundNet, a deep learning model designed for bird vocalization detection. Trained on field data and open-access databases, BioSoundNet achieved AUC scores of 0.88-0.93 and average precisions of 0.87-0.97 across five datasets spanning various ecosystems, and effectively captured the temporal patterns of avian acoustic activity at different time scales. Our findings underline the importance of evaluating models in ecological contexts and to address the potential consequences of missing detections. Operating efficiently on standard computers, BioSoundNet is a robust tool for automated bird vocalization detection, providing a valuable resource for ecological phenology studies and acoustic dataset analysis.

Environmental variation among isolated populations can drive genetic differentiation by selection, while isolation alone results primarily in genetic drift. Genetic analyses can aid in identifying genetically isolated populations and population structure of a species across its range. Additionally, such analyses can provide indirect evidence of local adaptation through the comparison of allele frequencies at neutral and functional genetic markers, with the aim of identifying outlier loci consistent with the effects of selection. Here, we examine the genetic divergence and patterns of functional divergence among six breeding populations of arctic-breeding snow buntings (Plectrophenax nivalis). We genotyped 221 birds at 9 microsatellite markers and at 101 single nucleotide polymorphisms (SNPs) located within known-function genes. We identified substantial population differentiation using both marker types with relatively greater divergence and hence finer population structure using the microsatellite markers. While population structures resulting from the two marker types were in general agreement, functional SNPs showed evidence of stabilizing selection at both global and population pairwise levels, with a few key SNPs showing signatures of pairwise divergent selection, consistent with expectations of local adaptation. The observed complex and inconsistent pattern of pairwise divergence (selection) at key candidate-gene loci may reflect rapid environmental change decoupling locally adapted genotypes from actual local environmental conditions. Our work highlights microevolutionary changes that are likely to be very important not only in arctic-breeding songbirds, but in Arctic and Sub-Arctic vertebrates in general, which are experiencing strong environmental effects from accelerated climate change and human-induced stressors.