The Machine Learning Approach to Moment Closure Relations for Plasma: A Review

TL;DR

This review discusses recent machine learning methods for developing plasma closure models in fluid simulations, highlighting their potential to capture kinetic phenomena and the challenges involved.

Contribution

It provides a comprehensive overview of machine learning techniques for plasma closure relations, including equation discovery and neural network surrogates, and discusses future research directions.

Findings

Machine learning approaches can improve plasma closure models.

Challenges include ensuring physical consistency and interpretability.

Future research may focus on integrating physics-based constraints.

Abstract

The requirement for large-scale global simulations of plasma is an ongoing challenge in both space and laboratory plasma physics. Any simulation based on a fluid model inherently requires a closure relation for the high order plasma moments. This review compiles and analyses the recent surge of machine learning approaches developing improved plasma closure models capable of capturing kinetic phenomena within plasma fluid models. The purpose of this review is both to collect and analyse the various methods employed on the plasma closure problem, including both equation discovery methods and neural network surrogate approaches, as well as to provide a general overview of the state of the problem. In particular, we outline the challenges associated with machine learning based closure relations and the direction that future research might take in order to address these challenges.