Physics-Informed Transformation Toward Improving the Machine-Learned NLTE Models of ICF Simulations

TL;DR

This paper introduces physics-informed transformations to improve machine-learned NLTE models in ICF simulations, focusing on physically relevant error metrics to enhance model accuracy and efficiency.

Contribution

It proposes novel physics-informed transformations and error metrics that better align machine learning models with physical energy transport processes in ICF simulations.

Findings

Transformations yield smaller errors in principal component space.

Enhanced model accuracy with physics-informed error metrics.

Reduced computational time compared to traditional methods.

Abstract

The integration of machine learning techniques into Inertial Confinement Fusion (ICF) simulations has emerged as a powerful approach for enhancing computational efficiency. By replacing the costly Non-Local Thermodynamic Equilibrium (NLTE) model with machine learning models, significant reductions in calculation time have been achieved. However, determining how to optimize machine learning-based NLTE models in order to match ICF simulation dynamics remains challenging, underscoring the need for physically relevant error metrics and strategies to enhance model accuracy with respect to these metrics. Thus, we propose novel physics-informed transformations designed to emphasize energy transport, use these transformations to establish new error metrics, and demonstrate that they yield smaller errors within reduced principal component spaces compared to conventional transformations.