Share on Twitter
Print this article
Share by email
Computer scientists from the University of Massachusetts Amherst, in collaboration with biologists from the Cornell Lab of Ornithology, recently announced in the journal Methods in ecology and evolution a new predictive model that can accurately predict where a migrating bird will go next – one of the most difficult tasks in biology. The model is called BirdFlow, and while it’s still being refined, it should be available to scientists within a year and eventually be available to the general public.
“Humans have been trying to understand bird migration for a very long time,” says Dan Sheldon, professor of information and computer science at UMass Amherst, lead author of the paper and birdwatcher. “But,” adds Miguel Fuentes, lead author of the paper and graduate student in computer science at UMass Amherst, “it is incredibly difficult to get accurate, real-time information about the birds that are found, let alone on their exact destination.
Many past and current studies have tagged and tracked individual birds, providing invaluable information. But it’s difficult to physically tag enough birds – let alone cost – to form a picture complete enough to predict bird movements. “It’s really difficult to understand how an entire species moves across the continent with tracking approaches,” says Sheldon, “because they tell you the routes taken by certain birds captured in specific locations, but not how birds located in completely different places could move.”
In recent years, the number of community scientists monitoring and reporting sightings of migratory birds has exploded. Birdwatchers around the world contribute more than 200 million bird sightings annually through eBird, a project managed by the Cornell Lab of Ornithology and international partners. It is one of the largest biodiversity-related science projects in existence and has hundreds of thousands of users, facilitating state-of-the-art species distribution modeling through the lab’s eBird Status & Trends project. “eBird data is amazing because it shows where birds of a given species are each week across their range,” says Sheldon, “but it doesn’t track individuals, so we have to infer the routes birds take. individual birds to better explain the species level models.
Observed movements of woodcocks tracked by GPS (single thick path) and simulated trajectories (thin paths) for 2,500 simulated birds from the same starting location as the observed birds. Image courtesy of Fuentes et al., 10.1111/2041-210X.14052
BirdFlow draws on eBird’s Status & Trends database and its estimates of relative bird abundance, then runs this information through a probabilistic machine learning model. This model is optimized with real-time GPS and satellite tracking data so that it can “learn” to predict where individual birds will move next during their migration.
BirdFlow outperforms other tracking models
Researchers tested BirdFlow on 11 North American bird species, including American Woodcock, Wood Thrush and Slender-backed Hawk, and found that not only did BirdFlow outperform other models for tracking migration of birds, but that it could also accurately predict migration flows without relying on real-time data. GPS and satellite tracking data, making BirdFlow an invaluable tool for tracking species that can literally fly under the radar.
“Birds today are undergoing rapid environmental change and many species are in decline,” says Benjamin Van Doren, postdoctoral researcher at the Cornell Lab of Ornithology and co-author of the study. “With BirdFlow, we can unite different data sources and build a more complete picture of bird movements,” adds Van Doren, “with exciting applications to guide conservation action.”
With an $827,000 grant from the National Science Foundation, Sheldon and his colleagues are improving BirdFlow and plan to release a software package aimed at ecologists later this year, with future development aimed at visualization products for the general public.
Thanks to the University of Massachusetts Amherst for this news.
New tracking tools reveal the secrets of bird migration
