machine learning, behavioral ecology, macroecology
845 677-7600 x135
Barbara Han’s research is at the intersection of ecology, computing, and global health. Han uses machine learning to forecast outbreaks of new zoonotic diseases – those that ‘jump’ from animals to humans. Of more than a billion cases of human illness reported each year, the majority are attributed to zoonotic pathogens.
Han employs complex computer algorithms to analyze patterns and processes in nature that could result in the next Ebola, SARS, or West Nile virus outbreak. Some of these models compare traits of known animal disease carriers – size, diet, reproductive habits, biogeography – with thousands of species not yet known to carry disease, in order to predict which animals might become disease carriers in the future. Han also works on projects that predict where and when diseases could emerge; other research investigates why and how some species transmit more zoonoses to humans than others.
Research like Han’s has the potential to become a valuable tool for public health officials. Predicting and preempting the arrival of a new zoonotic disease will save lives. This technology could also impact land management decisions, as it becomes obvious that diseases are more likely to emerge from certain habitats.
Han has partnered with diverse collaborators at IBM and NASA to advance research on global disease prediction. She contributes to efforts led by WHO and the US Government to apply this research to disease preemption
Millions of lives are lost each year to illnesses caused by pathogens that spread from wildlife and domesticated animals to people. Too often, outbreaks of Ebola, Nipah, Zika, and other zoonotic diseases force communities into reactive mode: scrambling to contain their spread and minimize suffering.
How do diseases spread from animals to humans? Is it possible to forecast where disease outbreaks will occur and when they will blow up into major health crises?
Disease ecologist Dr. Barbara Han discusses how, with the help of artificial intelligence and machine learning, her team analyzes data on animals, disease, and geography to pinpoint areas at risk of future disease outbreaks.
Tao Huang is the data manager and a programmer in the Han lab, where he manages multiple data streams, facilitates data science and collaborations, and builds and manages code and data libraries to support diverse research in infectious disease ecology. In previous research, Tao applied watershed models and statistical analyses to understand land use, water quality, and ecosystem service dynamics. He earned his M.S. in environmental science from the University of New Hampshire in 2016. For his Master’s research, he used a river network model to simulate the fate and transport of fecal indicator bacteria. Prior to conducting research in the U.S., he applied watershed models to predict water quality and ecosystem service changes in Taiwan. His research interests include macroecological modeling of infectious disease, and applying computational approaches to the protection of human health and biodiversity conservation.