In 2010 and with a decade more of evolution and advance of the Internet and artificial intelligence and big data research, ornithologists and computer scientists from Cornell University and Oregon State University proposed a respective and novel approach to the National Science Foundation “Cyber-enabled discovery initiative.” The result was a NSF award from 2011-2016 that allowed BirdCast to evolve from its early phase to what it is at present.
Techniques, Infrastructure, and Visualizations
Collaborators at Oregon State University and University of Massachusetts Amherst proposed two innovative machine-learning techniques: Collective Graphical Models (CGMs) and Semi-Parametric Latent Process Models (SLPMs). These techniques would provide the abilities 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. The BirdCast team also planned to develop 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. Research furthered plans for understanding relationships between radar and eBird data and inspired new NSF awards (for example, see Dark Ecology and BirdVox). The project also proposed novel web-based data visualizations for communicating the migration predictions generated by BirdCast to the general public. The BirdCast site has provided these types of interpretation and information since 2012; but beginning in spring 2018, the project began providing forecast and live bird migration maps that elegantly represented the original vision and spirit of the project’s 1999 intent and the grandeur of bird movements at the continental scale spanning two decades.
