Joseph Kump
I am a PhD student in the Oden Institute at the University of Texas at Austin. My research is in the design and optimization of linear solvers, and the use of automatic differentiation to enable data driven methods like parameter estimation and scientific machine learning, with an emphasis on applications in ocean and climate modeling.
Session
Ocean models simulate complex physics, but struggle from inherent limitations and under-resolved phenomena. This motivates the use of inverse and machine learning methods to inform models with data. We have implemented automatic differentiation in the Ocean modeling package Oceananigans.jl, through the use and enhancement of compiler tools Enzyme.jl and Reactant.jl. Using these open-source packages, we generate gradients for applications like parameter estimation and embedded ML techniques.