Ecological processes such as bird migration are complex, difficult to measure, and occur at the scale of continents, making it impossible for humans to grasp their broad-scale patterns by direct observation. However, novel data sources—such as large sensor networks and millions of bird observations reported by human “citizen scientists”—are providing new opportunities to understand ecological phenomena at very large scales. The ability to fit models, test hypotheses, make predictions, and reason about human impacts on biological processes at this scale promise to revolutionize ecological science and environmental policy.
In this talk, I will present novel algorithmic approaches to overcome challenges throughout the “pipeline” from low-level data interpretation to model fitting to high-level decision-making in large-scale ecological science, including: (1) biological interpretation of NEXRAD weather radar, (2) probabilistic modeling of bird migration using citizen science data and (3) optimizing land purchases to support the recovery of endangered species. I will highlight contributions from this work that extend well beyond ecology, including a very general optimization framework for maximizing the spread of a cascading process in a network, and a formalism called Collective Graphical Models for efficiently reasoning about probabilistic models of large populations of individuals when only aggregate data is available.
Daniel Sheldon is a postdoctoral fellow in the School of EECS at Oregon State University, where he holds an NSF fellowship in Bioinformatics. His primary research interests are machine learning and probabilistic modeling applied to large-scale problems in ecology and computational sustainability. Other research interests include web search and reputation systems, optimization, statistics, and network modeling. He completed his Ph.D. in computer science at Cornell University in 2009. Prior to that, he received an A.B. in mathematics from Dartmouth College in 1999, and worked at Akamai Technologies and then DataPower Technology between 1999 and 2004.