BirdCast will allow, for the first time, real-time predictions of bird migrations: when they migrate, where they migrate, and how far they will be flying.
Knowledge of migratory behavior will aid conservation on the ground by informing decisions for placement of wind turbines and identifying nights on which lighting of tall buildings could be reduced to prevent the deaths of millions of birds. Accurate migration models also have broader application, allowing researchers to understand behavioral aspects of migration, how migration timing and pathways respond to changing climate, and whether linkages exist between variation in migration timing and subsequent changes in population size.
New Machine-learning Techniques
We propose to develop two innovative machine-learning techniques: Collective Graphical Models (CGMs) and Semi-Parametric Latent Process Models (SLPMs). When combined, these models will reconstruct and predict the behavior of ~400 species of migrating birds across North America. The resulting model will be able to identify the complex conditions governing the dynamics of migration behavior, including choice of migratory pathways, the factors that influence when birds migrate, and the speed and duration of each night’s movements. In addition, we will improve our machine learning methods for identifying bird species from their flight calls (unique calls given by each species during nocturnal migration).
New Data Infrastructure
We will develop a new interoperable data infrastructure for synthesizing bird observations, flight calls, radar data, and covariate data from multiple sources including satellite imagery, weather, and human population data. By the end of the grant period, we will provide daily forecasts of bird migration (a daily BirdCast), as well as interactive tools for visualizing and understanding the models. We will also provide general-purpose open-source implementations of CGMs and SLPMs.
New Data Visualizations
Finally, we will develop novel web-based data visualizations for communicating the migration predictions generated by BirdCast to the general public, resulting in a strong potential for outreach and education, with opportunities for informal education regarding computer science, ecology, and conservation. These same visualization tools will provide an appealing avenue for school classes and the general public to “see” the dynamic processes of bird migration in action, strengthening their connection to the natural world. Further, by integrating these applications into existing education and outreach activities already managed by the Cornell Lab of Ornithology, we can introduce vast new audiences to exciting and important advances in computer science.