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

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. We survey two methodological families: neural-network surrogates (from multilayer perceptrons to Fourier neural operators, the latter recently reproducing both linear and non-linear Landau damping online within a fluid solver) and equation-discovery methods such as sparse regression; and organise the studies by whether they are tested offline against reference data or online within a time-evolving solver. We outline the challenges associated with machine-learning closures, including off-diagonal pressure-tensor accuracy, generalisation beyond the training distribution, and stable integration into large-scale simulations, and the directions future research might take to address them.

58 pages, 6 figures

References in corpus (48)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• Machine Learning for Fluid Mechanics
• B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data
• A high-bias, low-variance introduction to Machine Learning for physicists
• Gradient-enhanced physics-informed neural networks for forward and inverse PDE problems
• Enhancing Computational Fluid Dynamics with Machine Learning
• PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
• SINDy-PI: A Robust Algorithm for Parallel Implicit Sparse Identification of Nonlinear Dynamics
• Weak SINDy For Partial Differential Equations
• PySINDy: A comprehensive Python package for robust sparse system identification
• Vlasov methods in space physics and astrophysics
• DeepMoD: Deep learning for Model Discovery in noisy data
• Using Noisy or Incomplete Data to Discover Models of Spatiotemporal Dynamics
• Reduced fluid-kinetic equations for low-frequency dynamics, magnetic reconnection and electron heating in low-beta plasmas
• Phase mixing vs. nonlinear advection in drift-kinetic plasma turbulence
• Comparison of multi-fluid moment models with Particle-in-Cell simulations of collisionless magnetic reconnection
• Data-driven discovery of reduced plasma physics models from fully-kinetic simulations
• Global Ten-Moment Multifluid Simulations of the Solar Wind Interaction with Mercury: From the Planetary Conducting Core to the Dynamic Magnetosphere
• A Landau fluid model for warm collisionless plasmas
• A posteriori learning for quasi-geostrophic turbulence parametrization
• An introductory guide to fluid models with anisotropic temperatures Part 1 -- CGL description and collisionless fluid hierarchy
• Darwin-Vlasov Simulations of magnetized Plasmas
• Viriato: a Fourier-Hermite spectral code for strongly magnetised fluid-kinetic plasma dynamics
• Fluid and gyrofluid modeling of low-${\beta }_e$ plasmas: phenomenology of kinetic Alfvén wave turbulence
• Machine Learning Surrogate Models for Landau Fluid Closure
• An introductory guide to fluid models with anisotropic temperatures Part 2 -- Kinetic theory, Padé approximants and Landau fluid closures
• Imbalanced kinetic Alfvén wave turbulence: from weak turbulence theory to nonlinear diffusion models for the strong regime
• ViDA: a Vlasov-DArwin solver for plasma physics at electron scales
• Neural network representability of fully ionized plasma fluid model closures
• Data-driven, multi-moment fluid modeling of Landau damping
• Data-driven modeling of Landau damping by physics-informed neural networks
• Local thermodynamics of a magnetized, anisotropic plasma
• Bridging hybrid- and full-kinetic models with Landau-fluid electrons: I. 2D magnetic reconnection
• Do we need to consider electron kinetic effects to properly model a planetary magnetosphere: the case of Mercury
• Machine-learning heat flux closure for multi-moment fluid modeling of nonlinear Landau damping
• In Search of a Data Driven Symbolic Multi-Fluid 10-Moment Model Closure
• Inverse cascade and magnetic vortices in kinetic Alfvén-wave turbulence
• Identification of high order closure terms from fully kinetic simulations using machine learning
• Data-driven discovery of a heat flux closure for electrostatic plasma phenomena
• A non-local fluid closure for modeling cyclotron resonance in collisionless magnetized plasmas
• Hyperbolic Machine Learning Moment Closures for the BGK Equations
• Critical comparison of collisionless fluid models: Nonlinear simulations of parallel firehose instability
• Machine-learning Closure for Vlasov-Poisson Dynamics in Fourier-Hermite Space
• Electron neural closure for turbulent magnetosheath simulations: energy channels
• Surrogate Modeling of Landau Damping with Deep Operator Networks
• Embedding physical symmetries into machine-learned reduced plasma physics models via data augmentation
• Electron Heat Flux and Whistler Instability in the Earth's Magnetosheath