作者: Benjamin M. Van Doren , Kyle G. Horton
DOI: 10.1101/293092
关键词:
摘要: Abstract Billions of animals cross the globe each year during seasonal migrations, but efforts to monitor them are hampered by irregularity and relative unpredictability their movements. We developed a bird migration forecast system with continental scope leveraging 23 years spring observations learn associations between atmospheric conditions intensity. Our models explained up 81% variation in intensity across United States at altitudes 0-3000 m, performance remained high when forecasting events 24-72 h into future (68-72% explained). infer that avian migratory movements frequently exceed 200 million individuals per night 500 peak passage. Accurately will allow stakeholders reduce collisions illuminated buildings, airplanes, wind turbines, predict under climate change scenarios, engage public.