BirdFlow: Learning seasonal bird movements from eBird data

Authors: Miguel Fuentes, Benjamin M. Van Doren, Daniel Fin, and Daniel Sheldon

Year: 2023

Publication: Methods in Ecology and Evolution

Publication Link: https://besjournals.onlinelibrary.wiley.com/doi/full/10.1111/2041-210X.14052

Keywords: big data, bird migration, forecasting, graphical models, movement ecology, species distributions

Abstract:

1. Large-scale
monitoring of seasonal animal movement is integral to science, conservation
and outreach. However, gathering representative movement data
across entire species ranges is frequently intractable. Citizen science databases
collect millions of animal observations throughout the year, but it is challenging to
infer individual movement behaviour solely from observational data.
2. We present BirdFlow, a probabilistic modelling framework that draws on citizen
science data from the eBird database to model the population flows of migratory
birds. We apply the model to 11 species of North American birds, using GPS and
satellite tracking data to tune and evaluate model performance.
3. We show that BirdFlow models can accurately infer individual seasonal movement
behaviour directly from eBird relative abundance estimates. Supplementing
the model with a sample of tracking data from wild birds improves performance.
4. Researchers can extract a number of behavioural inferences from model results,
including migration routes, timing, connectivity and forecasts. The BirdFlow
framework has the potential to advance migration ecology research, boost insights
gained from direct tracking studies and serve a number of applied functions
in conservation, disease surveillance, aviation and public outreach.

Leave a Reply

Your email address will not be published. Required fields are marked *