The Department of Biomedical Data Science invites you to attend a seminar in person on Thursday, October 8 from 11:00-12:00pm at DHMC, Auditorium H with Xiao Wu, PhD, Assistant Professor of Biostatistics, Columbia University. Extreme weather events, including wildfires and tropical cyclones, are becoming more frequent and intense, yet substantial gaps remain in understanding how their health and social consequences evolve over multiple years in affected communities. This talk introduces covariate-balanced synthetic control, a new causal inference approach that connects synthetic control with covariate balancing methods and incorporates tailored balance conditions to accommodate high-dimensional pre-exposure covariates, improving the feasibility and computational efficiency of estimation in large-scale environmental data. I will illustrate the approach through two applications: an analysis of satellite-based fire activity across California forests from 2000 to 2021, which found that low-intensity fires substantially reduce the risk of subsequent high-intensity wildfires, and an analysis of U.S. tropical cyclones from 2005 to 2018, which characterized changes in social vulnerability.
"Causal Machine Learning Methods to Assess Long-Term Impacts
of Extreme Weather Events and Policies”
Thursday, October 8 from 11:00am-12:00pm ET
Assistant Professor
Biostatistics
Columbia University
The presentation will take place both in person at DHMC, Auditorium H (and via Zoom).
Please write to biomedical.data.science@dartmouth.edu to request the Zoom login details.
Xiao Wu, PhD, is an Assistant Professor of Biostatistics at Columbia University and a Health AI Scientist at Meta. His research develops statistical, machine learning, and causal inference methods to address methodological challenges in health research, with particular emphasis on generating evidence and policy solutions to mitigate the health impacts of environmental and climate-related exposures. Dr. Wu is also interested in health technologies and AI evaluation for health applications. He earned his Ph.D. in Biostatistics from Harvard University and completed a Data Science Postdoctoral Fellowship at Stanford University. Named to the Forbes 30 Under 30 list, Dr. Wu has published in Science, the New England Journal of Medicine, The Lancet Planetary Health, and the Journal of the American Statistical Association, and his work has been featured by international media including The New York Times, National Geographic, Scientific American, and the Financial Times.