Internships

Jamie Kim ’24

Major

Civil and Environmental Engineering

Project Title

The Interface of Hydrology and Machine Learning: Generating Better Information for Decision-makers and Educating the Decision-makers of the Future

Certificate(s): Applications of Computing

Providing accurate information about our water sources is important for future decision-makers to make wise and sustainable plans concerning water management. However, due to climate change, future environmental conditions have become further unpredictable, making it challenging to understand our water supplies. Using both physics-based and data-driven modeling in combination is essential for predicting conditions, as both modeling methods have advantages and disadvantages. To inform the integration of these methods, I analyzed the correlations between pumping data and climate condition variables and determined how groundwater pumping affects water table depth. I focused on implementing a machine learning, data-driven model that used a regression-enhanced random forest method to estimate water table depth in New Jersey. In addition, as part of the educational aspect of the internship, I helped teach at The Watershed Institute’s Watershed Academy for High School Students where I introduced the idea of pattern recognition and discussed the importance of data quantity and quality for training, all of which are fundamental to machine learning. Through this experience, I learned various practical skills in machine learning and data analysis which I hope to utilize for my senior thesis and other future work.