Leveraging Machine Learning and Geo-tagged Citizen Science Data to Disentangle the Factors of Avian Mortality Events at the Species Level

Partly due to global climate change, extreme weather and natural hazards have increased dramatically during the recent decades. Those sudden environmental changes often cause significant impacts on the living species on the planet via directly affecting the population structures or indirectly causing habitat loss or fragmentations. In August - October 2020, tremendous mortalities of avian species were reported in the western and central US, likely resulting from winter storms and wildfires based on previous evidence. However, the differences of how different species might respond to the environmental changes were still poorly understood. In this study, we focused on three species that have been recorded with the highest death observations collected by citizen scientists (i.e., Wilson’s warbler, barn owl, and common murre) and employed the random forest model to disentangle their responses to the two environmental changes. We found the mortalities of Wilson’s warbler were primarily impacted by early winter storms, with more deaths identified in areas with a higher average of maximum daily snowfalls. Barn owl responded to both wildfire effects and winter storms but with more deaths identified in places with high wildfire-induced air pollution. Both events had mild effects on common murre. Mortalities of common murre may be related to high water temperature. Our findings highlight the species-specific responses to environmental changes, which can provide significant insights into the resilience of ecosystems to environmental change and avian conservations.