Bio

Shaivi is interested in applying mathematics and computer science to environmental challenges. Her work explores how machine learning and data-driven models can be used to understand and predict the behavior of pollutants in complex systems. She has worked on modeling remediation processes using real-world environmental data, analyzing how factors such as chemical conditions and microbial activity influence the breakdown of contaminants over time. She enjoys approaching environmental problems through a quantitative lens, combining techniques from statistics, optimization and machine learning to uncover patterns in large datasets. Beyond research, she is involved in building tools and programs that make technical knowledge more accessible, from designing user-focused applications to teaching coding and organizing STEM initiatives. In her free time, she enjoys swimming, reading and creating henna art.

Project: Simulating Heat Distribution and Layout Optimization in a Server Farm