no code implementations • 15 Sep 2020 • Alp Dener, Marco Andres Miller, Randy Michael Churchill, Todd Munson, Choong-Seock Chang
We investigate the physics-constrained training of an encoder-decoder neural network for approximating the Fokker-Planck-Landau collision operator in the 5-dimensional kinetic fusion simulation in XGC.
no code implementations • ICLR Workshop DeepDiffEq 2019 • Marco Andres Miller, Randy Michael Churchill, Choong-Seock Chang, Robert Hager
An encoder-decoder neural network has been used to accelerate the numerical solving of a partial integro-differential equation, the Fokker-Planck-Landau collision operator.