Improved Surrogates in Inertial Confinement Fusion with Manifold and Cycle Consistencies

TL;DR

This paper introduces physically consistent and cyclically consistent neural network surrogates for Inertial Confinement Fusion, improving accuracy, robustness, and data efficiency in modeling high-dimensional physical systems.

Contribution

It proposes a novel approach to training neural surrogates with manifold and cycle consistency constraints, enhancing their physical validity and performance.

Findings

Surrogates with manifold and cycle consistency outperform traditional models.

The approach improves robustness against sampling artifacts.

It achieves higher data efficiency in modeling ICF simulations.

Abstract

Neural networks have become very popular in surrogate modeling because of their ability to characterize arbitrary, high dimensional functions in a data driven fashion. This paper advocates for the training of surrogates that are consistent with the physical manifold -- i.e., predictions are always physically meaningful, and are cyclically consistent -- i.e., when the predictions of the surrogate, when passed through an independently trained inverse model give back the original input parameters. We find that these two consistencies lead to surrogates that are superior in terms of predictive performance, more resilient to sampling artifacts, and tend to be more data efficient. Using Inertial Confinement Fusion (ICF) as a test bed problem, we model a 1D semi-analytic numerical simulator and demonstrate the effectiveness of our approach. Code and data are available at https://github.com/rushilanirudh/macc/