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.

Aim: To test whether the occupancy of shorebirds has changed in the eastern Canadian Arctic, and whether these changes could indicate that shorebird distributions are shifting in response to long-term climate change Location: Foxe Basin and Rasmussen Lowlands, Nunavut, Canada Methods: We used a unique set of observations, made 25 years apart, using general linear models to test if there was a relationship between changes in shorebird species’ occupancy and their Species Temperature Index, a simple version of a species climate envelope. Results: Changes in occupancy and density varied widely across species, with some increasing and some decreasing. This is despite that overall population trends are known to be negative for all of these species, based on surveys during migration. The changes in occupancy that we observed were positively related to the Species Temperature Index, such that the warmer-breeding species appear to be moving into these regions, while colder-breeding species appear to be shifting out of the regions, likely northwards. Main Conclusions: Our results suggest that we should be concerned about declining breeding habitat availability for bird species whose current breeding ranges are centred on higher and colder latitudes.

Many populations of long-distance migrant shorebirds are declining rapidly. Since the 1970s, the Lesser Yellowlegs (Tringa flavipes) has experienced a pronounced reduction in abundance of ~63%. The potential causes of the species’ decline are complex and interrelated yet understanding the timing of migration and seasonal routes used by this species will aid in directing conservation planning to address potential threats. During 2018–2021, we tracked 118 adult Lesser Yellowlegs using GPS satellite tags deployed on birds from five breeding and two migratory stopover locations spanning the boreal forest of North America from Alaska to eastern Canada. Our objectives were to quantify migratory connectivity and identify key stopover and non-breeding locations. Individuals tagged in Alaska and central Canada followed similar southbound migratory routes through the Prairie Pothole Region of North America, whereas birds tagged in eastern Canada completed multi-day transoceanic flights covering distances of >4,000 km across the Atlantic between North and South America. Upon reaching their non-breeding locations, Lesser Yellowlegs populations overlapped, resulting in weak migratory connectivity. Lastly, freshwater and agricultural habitats of the Prairie Pothole region supported the highest proportion of Lesser Yellowlegs during southbound migration. Our findings suggest that while Lesser Yellowlegs travel long distances and traverse numerous political boundaries each year, the breeding population from which an individual originates likely has the greatest influence on which threats birds experience during migration. Further, the species’ dependence on wetlands in agricultural landscapes during migration may make them vulnerable to threats related to agricultural practices, such as pesticide exposure.