Neural Network Surrogate Models for Absorptivity and Emissivity Spectra of Multiple Elements

TL;DR

This paper develops neural network surrogate models to efficiently predict the absorptivity and emissivity spectra of multiple elements, significantly reducing computational costs in high energy density physics simulations.

Contribution

It extends previous work by creating a combined surrogate model for multiple elements using autoencoders, enhancing efficiency in spectral calculations.

Findings

Successful development of a multi-element surrogate model

Reduction in computational time for opacity calculations

Potential for broader application in high energy density physics simulations

Abstract

Simulations of high energy density physics are expensive in terms of computational resources. In particular, the computation of opacities of plasmas in the non-local thermal equilibrium (NLTE) regime can consume as much as 90\% of the total computational time of radiation hydrodynamics simulations for high energy density physics applications. Previous work has demonstrated that a combination of fully-connected autoencoders and a deep jointly-informed neural network (DJINN) can successfully replace the standard NLTE calculations for the opacity of krypton. This work expands this idea to combining multiple elements into a single surrogate model with the focus here being on the autoencoder.