Steve Kelling’s primary focus is to coordinate a team of ornithologists, project managers, statisticians, application developers, and data managers to develop programs, tools, and analyses to gather, understand, and disseminate information on birds and the environments they inhabit. His responsibilities revolve around four broad topics: the management of eBird, a citizen-science project that gathers millions of bird observations from around the globe; the use of novel digital library strategies to create global communities of interested users centered around primary scientific references; the organization of the rich data resources of the bird-monitoring community and integrating these resources within existing bioinformatic infrastructures; and using unique statistical and computer science strategies to analyze the distribution and abundance of wild bird populations.
Tom Dietterich leads the development and application of advanced machine learning algorithms to model bird migration. These algorithms analyze the data provided by eBird volunteers, weather radar imagery, and weather forecasts to discover migration patterns and understand the factors that affect the speed and direction of bird flight during migration. Dietterich is President-Elect of the Association for the Advancement of Artificial Intelligence.
Wesley Hochachka is a senior research associate at Cornell University who has studied many aspects of the ecology and evolutionary biology of birds. Much of his research has revolved around identifying patterns and inferring processes over long time periods or large spatial extents. One of his current focuses is on the use of volunteer-collected (citizen science) data in order to understand the factors that determine where individual species live and why their distributions might change over time. Much of this work is as a member of the team that works on the analyses of data from eBird and the Avian Knowledge Network. The second current focus of his work is in disease ecology, as a member of a long-term collaboration that is studying the relationship between one finch species and a bacterial pathogen that jumped from poultry to these finches and subsequently caused substantial population declines in its new host.
Andrew Farnsworth is a Research Associate in the Information Science program. His primary focus for the project is migration biology, with a background in the ecology and evolution of migration, bioacoustics (flight calls, in particular), and radar ornithology. Andrew’s current research has focused on understanding calling phenology in vocal, nocturnal migrants, detection and classification of flight calls and wind-wildlife interactions. He began birding at age 5, and quickly developed an interest in bird migration. He completed a M.S. in Zoology with Dr. Sidney Gauthreaux using radar and acoustic technologies, followed by a Ph.D. in Ecology and Evolutionary Biology with Dr. John Fitzpatrick that focused heavily on flight call ecology, evolution, and application.
The primary goal of Professor Sheldon’s research is to develop algorithms to understand and make decisions about the environment using large data sets. He seeks to answer foundational questions (what are the general models and principles that underlie big data problems in ecology?) and also to build applications that transform large-scale data resources into scientific knowledge and policy. Some examples of his work include: spatial optimization to conserve endangered species, continent-scale modeling of bird migration, and biological interpretation of weather radar data across the US. Methodologically, Professor Sheldon’s primary interests are machine learning, probabilistic inference, and network modeling. His work has contributed broadly applicable new approaches for reasoning about aggregate data in probabilistic graphical models, and for optimization of diffusion processes in networks.
Theo is a machine learning researcher working together with the CLO on the areas of automatic flight call detection and classification, and active learning techniques for the eBird human-computer learning network. He is a member of the Institute for Computational Sustainability (ICS) at Cornell and his primary responsibilities include conducting research, supervising computer science master’s students and assisting with administration duties at ICS.
Kevin’s technical areas of interest are geospatial programming, high performance and parallel computing, data modeling, and database centric application development. His primary objective is the application of software engineering to facilitate discovery in conservation and biological sciences.
Giles Hooker’s primary focus is on the interface of mathematical models for biological processes and data observed from them. He has particular expertise in using machine learning methods, functional data analysis and nonlinear dynamics. A particular focus of his research is in the interface of data mining with statistics, assessing the statistical evidence for patterns found in data and using machine learning models within more classical statistical modeling frameworks. His work is applied in ecology, epidemiology, evolution and in modeling large-scale bird ecology.
Rich Caruana is Senior Researcher at Microsoft Research. Most of his research is in machine learning and data mining, and in the application of these to challenging problems in medical decision making and ecology. Rich has collaborated with Cornell’s Lab of Ornithology on a number of projects, and now serves as an external advisor on BirdCast. Recently Rich has begun a new collaboration with members of the BirdCast Team to investigate methods for providing ground truth observations of birds in flight to help calibrate radar measurements.
Frank A. La Sorte is a researcher ecologist whose work focuses on exploring the patterns and dynamics of biological diversity across space and time at continental to global scales. Currently he is developing a collaborative project to examine population-level migration trajectories of North American birds using the eBird database. The goal of this work to provide integrative and comprehensive scientific insights that will inform our current understanding of the biological phenomenon of avian migration. This research project provides unique opportunities to test and refine current migration theory and much needed information to support better informed policy and conservation initiatives.
David Nicosia has been a meteorologist with NOAA for over 20 years after receiving his B.S and M.S in Meteorology from Penn State. Dave has worked many severe weather and flood events and has published numerous papers in meteorology. Dave also has been an avid birder for most of his life and is a leader for Cornell’s Lab of Ornithology’s Spring Field Ornithology class and also leads birding field trips for the Broome Naturalist’s Club.
Liping Liu brings expertise in machine learning and probabilistic graphical models to the project. In previous work with Rebecca Hutchinson, he developed an R package for fitting latent variable models with boosted regression trees. He will be extending this work to create the Semi-Parametric Latent Process Models required for BirdCast.
Tao Sun’s research interests include machine learning and probabilistic graphical models. He has contributed to BirdCast by developing a synthetic data generator for weather-dependent bird migration, and by developing and testing different algorithms for approximate inference in Collective Graphical Models. He will continue this line of work to scale inference algorithms up to continent-sized problems, and to explore other applications and extensions of Collective Graphical Models.
Benjamin Van Doren is a sophomore at Cornell University studying Ecology and Evolutionary Biology. He is fascinated by bird migration and enjoys using computers to shed light on biological questions. His research into the phenomenon of morning flight was recognized last year when he won fifth place in the national Intel Science Talent Search in Washington, D.C.
Jeffrey Geevarghese is a masters student interested in machine learning and its applications. He is currently a research assistant with the Department of Computer Science, University of Massachusetts, Amherst. He has contributed to BirdCast by developing a dataset that summarizes bird migration information from weather radar data. He will extend this work to develop robust systems for automated analysis of weather radar data for studying bird migration patterns.