I am currently a Research Associate at the Cooperative Institute for Research in Environmental Sciences (CIRES) and NOAA's Physical Sciences Lab (PSL). The main goal of my research is to develop Artificial Recurrent Neural Networks that can make accurate predictions of oceanic quantities, such as sea surface temperature or current speeds. I am working with Steve Penny and PSL's Attribution and Predictability Assessments (APA) group to integrate these neural networks into modern data assimilation methods to enable computationally efficient, robust, data-driven weather forecasts. The eventual goal is to integrate our developments into the Hurricane Analysis and Forecast System (HAFS).
Before joining PSL, I obtained my Ph.D. in Computational Science, Engineering, and Mathematics from the Oden Institute at UT Austin. My graduate work focused on quantifying uncertainties that are inherent to ocean models, and I implemented a generic, adjoint-based framework to propagate these uncertainties onto predictions from the MIT general circulation model. I used this framework to show how sparse observations of the ocean state reduce uncertainty in simulation-based estimates of ocean driven melting underneath the Pine Island ice shelf, which is fed by one of the fastest flowing glaciers in Antarctica. The results showed how valuable observations in this region are for constraining modeled quantities.
Broadly speaking, I am motivated to develop open source computational tools that help us understand oceanographic processes relevant to the climate system.When I'm not working, I love to go rock climbing, skiing/snowboarding, trail running, and cycling in the beautiful Colorado outdoors.