Hello, I'm

I'm a mathematics and physics undergraduate at the University of Tennessee with a strong bias toward problems that sit at the intersection of theory, computation, and reality. My work revolves around using mathematical structure and machine learning to extract insight from complex physical systems, especially in areas where brute-force simulation alone starts to fail. I spend most of my time moving between proofs, code, and numerical experiments, trying to understand not just what works, but why it works.

My current focus is scientific machine learning for physics applications, particularly in neutrino astrophysics and dynamical systems. I build ML pipelines that respect physical constraints, train on large simulation-derived datasets using HPC resources, and treat models as tools for analysis rather than magic boxes. Outside formal research, I pursue independent projects spanning applied geometry, numerical methods, reinforcement learning, and quantum systems, largely driven by curiosity and an intolerance for shallow explanations.

More broadly, I'm interested in deep mathematical structure and its ability to unify seemingly unrelated problems. Whether that means analytic techniques, geometric formalisms, or carefully engineered learning systems, the goal is the same: develop tools that scale understanding, not just computation. This site is where I document that process, along with the projects, ideas, and occasional hard-won lessons that come with it.