Dr. Aaron Hill is a professor of meteorology in the School of Meteorology at the University of Oklahoma. His research interests include weather forecasting, data assimilation, numerical weather prediction, predictability of severe convective weather, artificial intelligence and machine learning, Python programming, innovative observing systems, and operational weather forecasting tools. Dr. Hill leads the CHAOS research group which specializes in Convection and weather Hazards with Artificial intelligence, Observations, and Simulations. The group is currently involved in developing machine learning tools for high-impact weather forecasting, exploring predictability of storms in warming climates, and understanding the dynamics of tornadogenesis in Quasi-Linear Convective Systems. Interested in joining the CHAOS group? Contact Dr. Hill: ahill@ou.edu
PhD in Geosciences, 2019
Texas Tech University
MS in Atmospheric Science, 2014
Texas Tech University
BS in Atmospheric Science; Minor in Applied Mathematics, 2012
University of Washington
Classes taught:
Full list of presentations here
Hill, A. J. and R. S. Schumacher, 2024: Medium-Range Excessive Rainfall Prediction with Machine Learning. EGU General Assembly 2024, Vienna, Austria.
Gagne II, D. J., and Coauthors, 2024: Lessons Learned from Building Real-Time Machine Learning Testbeds for AI2ES. 14th Conference on Transition of Research to Operations, Baltimore, MD.
Green, M. R. L., A. J. Hill, and R. S. Schumacher, 2024: Understanding Training Data Components for Excessive Rainfall Machine-Learning Models: A look inside the Unified Flooding Verification System. 23rd Annual AMS Student Conference, Baltimore, MD.
Mazurek, A. C., R. S. Schumacher, and A. J. Hill, 2024: When Do Machine Learning Forecasts Succeed and Fail? Evaluating Synoptic Regimes Associated With a Random Forest’s Good and Bad Severe Weather Predictions. 14th Conference on Transition of Research to Operations, Baltimore, MD.
Mazurek, A. C., A. J. Hill, R. S. Schumacher, and H. J. McDaniel, 2024: Ingredients-Based Explainability: Using Tree Interpreter to Disaggregate a Random Forest’s Severe Weather Predictions. 23rd Conference on Artificial Intelligence for Environmental Science, Baltimore, MD.