Hurricanes drive bird displacement revealed by deep learning species distribution models

Hurricanes are increasing in frequency and intensity under climate change, driving rapid and cascading transformations in coastal ecosystems. In affected regions, storm-driven flooding can restructure habitats and facilitate the spread of invasive species, with impacts propagating across trophic levels. Because birds link terrestrial and aquatic systems, understanding hurricane-driven displacement is critical for biodiversity monitoring and adaptive conservation planning. We develop an adaptive stratified deep learning framework to analyze citizen-science observations and quantify hurricane impacts on 332 bird species. The model achieves high predictive performance while jointly capturing abiotic and biotic niche structure, enabling the generation of fine-scale maps of post-hurricane habitat suitability and species redistribution. Our results suggest that projected bird displacement is contingent on long-term trajectories of climate change and sea-level rise, reflecting the interaction of acute disturbance and chronic environmental change. Vulnerability varies systematically across functional morphology groups and hurricane seasons: medium-sized, medium-long-winged, and granivorous species exhibit greater resilience, whereas winter emerges as a critical bottleneck for maintaining structural habitat complexity. Prioritizing winter habitat quality and protecting refugia adjacent to agricultural lands may therefore yield disproportionate conservation benefits as hurricane intensity increases. Sheltering and rebound patterns further demonstrate that scenario contrasts are critical for coastal conservation, supporting a shift from static protection toward dynamic, surge-aware strategies. Collectively, this work provides a scalable analytical framework for proactive, climate-adaptive decision-making under intensifying extreme events.