Cornell, UMass researchers develop computer model to predict migratory patterns of birds

Researchers from the Cornell Lab of Ornithology and the University of Massachusetts, Amherst have developed a new computer model that uses machine learning to predict the migratory patterns of birds.

According to a report by the Cornell Chronicle, this finding could offer insight into migration timing, stopover sites, bird response to climate change, light pollution and more. 

The model is called BirdFlow and is designed to learn patterns and variations in movement for individual species. This fills the gaps in understanding what has occurred in other traditional methods such as satellite tracking, which tracks only a limited number of birds. 

The model processes data from multiple sources that include weekly estimates of birds from eBird data submitted by birdwatchers and satellite tracking data, checking on locations from week to week. BirdFlow projects average travel routes for each species several weeks into the future, given a starting time and location.

“We’ll be able to unravel the routes that birds take, from their breeding grounds to stopover points, to wintering grounds and back without having to capture birds and attach tracking devices. Understanding these connections is critical to learning why some populations are doing poorly and some are doing well,” said Adriaan Dokter of the Cornell Lab, who is co-leading the BirdFlow project. 

The Cornell Chronicle report said that the team will work to improve BirdFlow and plan to release a software package for ecologists later this year. 

The research was funded by the National Science Foundation, a Cornell Presidential Postdoctoral Fellowship, the Leon Levy Foundation, the Wolf Creek Charitable Foundation, the Pittsburgh Supercomputing Center and the Massachusetts Technology Collaborative.

The researchers believe BirdFlow can offer vital information about bird movements and guide targeted conservation actions.

“Using BirdFlow to process multiple data sources will paint a more complete picture of bird movements to guide targeted conservation actions,” said Benjamin Van Doren, a study co-author and Cornell Lab postdoctoral researcher.

BirdFlow has the potential to enhance the understanding of bird migration and contribute to conservation efforts, plus offer insights into what affects bird populations, Doren added.