Ashley DeFrates ’25
Civil and Environmental Engineering
The Interface of Hydrology and Machine Learning: Generating Better Information for Decision-makers and Educating the Decision-makers of the Future
Meteorological forcings are the weather inputs that drive hydrological models and govern the behavior of water in hydrologic simulations. Therefore, the accuracy of a model is heavily dependent on the accuracy of the forcings used in its development. My research focused on analyzing the temperature and precipitation forcing products used in the ParFlow-CONUS2 model, an integrated hydrologic model developed by the Integrated GroundWater Modeling Center that resolves groundwater flow across the United States at 1 km resolution. I compared forcing products to observed data for multiple water years, making visual representations of spatial statistics such as relative bias. In addition to this research, I also helped develop and deliver educational modules at The Watershed Institute’s Watershed Academy for High School Students. It is becoming increasingly important that we understand our groundwater resources as the impacts of climate change persist, making both hydrologic modeling and scientific education crucial in the fight for a sustainable future. Engaging in this morally fulfilling work while improving my coding and scientific communication skills made this project a rewarding experience that inspired me to pursue further studies in hydrology.
Water and the Environment
Integrated GroundWater Modeling Center (IGWMC), Department of Civil and Environmental Engineering, Princeton University - Princeton, New Jersey
Reed Maxwell, William and Edna Macaleer Professor of Engineering and Applied Science, Professor of Civil and Environmental Engineering and the High Meadows Environmental Institute; Lisa Gallagher, Education and Outreach Specialist, IGWMC, Department of Civil and Environmental Engineering