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

2025-11-27

AI Summary

In large-scale global plasma simulations, conventional fluid models face fundamental limitations in accurately closing high-order moments and capturing kinetic effects. This paper provides a systematic review of recent advances in machine learning–driven plasma closure modeling. It comparatively analyzes two dominant paradigms—equation discovery (e.g., symbolic regression) and neural network surrogate models—highlighting critical challenges concerning physical consistency, generalizability, and interpretability. To address these, we propose a synergistic modeling framework that integrates prior physical constraints with data-driven learning, yielding novel closure relations that balance accuracy, robustness, and transferability. Our approach establishes a rigorous theoretical foundation and practical methodology for developing efficient and reliable large-scale plasma simulations. By bridging physics-informed learning with kinetic fidelity, this work significantly advances the standardization and deployment of data-driven plasma modeling in computational plasma physics.

Technology Category

• Machine Learning: Multimodal Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Game Theory and Economic Paradigms: Adversarial Learning

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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 highlight the challenges of developing a data-driven closure as well as the direction future work should take toward addressing these challenges, in the pursuit of a computationally viable large-scale global simulation.

Problem

• Developing machine learning-based closure relations for plasma fluid models
• Capturing kinetic phenomena within large-scale global plasma simulations
• Addressing challenges in data-driven closure for computationally viable simulations

Innovation

• Machine learning develops improved plasma closure models
• Equation discovery and neural network surrogate methods used
• Data-driven closure enables large-scale global plasma simulations