About

I build machine learning models that help scientists understand and predict how Earth systems change over time. I’m a Postdoctoral Research Scientist at the University of Hawaiʻi at Mānoa, working with Dr. Brian Powell.

Research Focus

My work sits at the intersection of machine learning and scientific modeling. The core challenge I return to is: how do you build models that learn from data while still respecting what we already know about how systems behave?

This takes a few forms in practice. I develop methods that make forecasting systems faster by replacing their most computationally expensive components with data-driven models, while remaining faithful to the underlying science. I also work on discovering structure directly from data: identifying the underlying equations that govern how a system evolves, rather than assuming them upfront.

Data assimilation, the process of combining model predictions with real-world observations to estimate a system’s current state, is one of the central settings where this question becomes most important. Both the surrogate modeling work and the equation discovery work ultimately serve this goal: the better and faster our models are, the more effectively we can combine them with observations to track how a system is actually evolving.

Background

I completed my PhD in Computational Engineering at Durham University in 2023, where I developed methods to automatically discover governing equations from data. This work produced the ARGOS R package and a publication in Communications Physics.

I also hold an M.S. in Data Science from Northwestern University and a B.A. in Statistics and Mathematics from Wittenberg University.

Recent Recognition

I received the Pacific Islands Impact Award at the Accelerating Research in the Age of AI: A Synergistic Workshop with Google (Google–UH, March 2026) for work on physics-informed neural networks for ocean modeling and data assimilation.