Jane Castleman ’25
The Interface of Hydrology and Machine Learning: Generating Better Information for Decision-makers and Educating the Decision-makers of the Future
Certificate(s): Environmental Studies, Technology and Society
Estimating water table depth (WTD) across the contiguous United States is important in providing reliable information to water decision-makers and producing inputs for predictive models. WTD predictions are increasingly being performed via machine learning to reduce the computational expense of using physics-based models. For my project, I compared the effectiveness of using observational data as opposed to simulated data as the input for machine learning models. I then tested the ability of the machine learning model to predict WTD with different sets of training and testing data. Each set of data consisted of averaged data from one week of observations. Overall, using observational data for the prediction of WTD could be a promising method for generating reliable information about WTD for water management and climate futures. Another project goal was to inform the water decision-makers of the future. To do this, we developed and implemented a water and climate academy for local high schoolers. In this program, we taught students the mathematical fundamentals of machine learning, its basis in pattern recognition, and the importance of good data in machine learning.
Water and the Environment
Integrated GroundWater Modeling Center, Department of Civil and Environmental Engineering, Princeton University - Princeton, New Jersey
Reed Maxwell, Professor of Civil and Environmental Engineering and the High Meadows Environmental Institute; Lisa Gallagher, Education and Outreach Manager, High Meadows Environmental Institute