Hometown: Santa Barbara, CA
Degree Earned: Ph.D. in Geology
Research Overview: Here at The University of Alabama I have been researching the use of machine learning-based models for forecasting hydrologic conditions across the United States. I have designed, developed and implemented different methods of using machine learning on its own, and in combination with physics-based hydrology models, to predict soil moisture, surface energy fluxes, streamflow and flood extent. I have tested these methods on long term simulations, as well as the most extreme flood events in recent years. With the overwhelming success of machine learning, I pivoted my focus to explore how we can best use this technology in an operational setting, i.e., making predictions and forecasts in near real-time to aid decision making and water resources management. I had the great fortune to work with both NASA and NOAA (on the UA Campus at the U.S. National Water Center) to integrate these methods into our nation’s hydrologic prediction systems.