Structure-preserving neural networks for the regularzied entropy-based closure of the Boltzmann moment system

arXiv:2404.14312v1 Announce Type: cross
Abstract: The main challenge of large-scale numerical simulation of radiation transport is the high memory and computation time requirements of discretization methods for kinetic equations. In this work, we derive and investigate a neural network-based approximation to the entropy closure method to accurately compute the solution of the multi-dimensional moment system with a low memory footprint and competitive computational time. We extend methods developed for the standard entropy-based closure to the context of regularized entropy-based closures. …

arxiv boltzmann cs.lg cs.na entropy math.na moment networks neural networks type