About

I am an Associate Research Scholar at Princeton University and member of the M2LInES project. I am using machine learning to improve ocean models.

Before joining the M2LInES team, I worked with the Ocean Transport and Eddy Energy Climate Process Team (CPT). My research with the CPT was focused on better understanding the ocean eddy energy cycle and improving mesoscale eddy parameterizations by making them energetically consistent. I have also worked on adjoint modeling and ocean state estimation within the ECCO project. Within the ECCO framework, I applied techniques from the computational sciences in order to quantify uncertainties in ocean state estimates and gain new insights into how to improve the global ocean observing system.

I am engaged in developing open-source Python tools to enable our community to perform efficient, reproducible, and open science. I am a PI in the DJ4Earth project, where we develop and use an open-source framework for universal differentiable programming in Julia, which integrates Bayesian inverse methods with scientific machine learning in Earth system models.

When I’m not doing research, I like being active in the outdoors. I love rock climbing, trail running, and backcountry skiing.