Research Interests

My research develops statistically rigorous methods for decision-making under uncertainty across multiple scientific domains, especially in settings where classical assumptions break down: non-Euclidean parameter spaces, massive physics simulators with intrinsic stochasticity, and limited historical data. I work collaboratively with domain scientists to build practical forecasting and uncertainty quantification tools that are both methodologically principled and operationally useful, including disease-agnostic ensemble learning for infectious disease prediction, modeling and understanding Solar Energetic Particle events for national security applications, and sensitivity analysis and bias correction for multi-fidelity discrete fracture network models. Alongside these applied efforts, I maintain an ongoing interest in the theory and computation of generalized fiducial and Bayesian inference, inference on differentiable manifolds and geometric perspectives on uncertainty, and methods based on Dempster-Shafer calculus. Across all areas, my goal is to deliver deployable methods with careful attention to reproducibility and open software.

Recent News

15 Jan 2026	Our disease-agnostic ensemble learning paper was accepted to Nature Communications.
01 Dec 2025	Served as Keynote Speaker at the Residential Colleges Symposium at Bucknell University.
15 Nov 2025	Presented a poster at Epidemics in San Diego, CA.
25 Jun 2025	My paper on the synthetic method of analogues was published in PLOS Computational Biology.
01 Jun 2025	My Dempster-Shafer multinomial inference manuscript received an R&R at JRSS-B.

View All

Brief Bio

I'm a born-and-raised Pittsburgh-er who traveled down south to pursue my dream of being a Statistics professor. When that dream changed, I headed westward. When I'm not thinking about math and coding, I'm swimming, dancing, and singing loudly in the shower.

Erdös-Bacon Number: 5