Identification of high order closure terms from fully kinetic simulations using machine learning

Abstract

Simulations of large-scale plasma systems are typically based on a fluid approximation approach. These models construct a moment-based system of equations that approximate the particle-based physics as a fluid, but as a result lack the small-scale physical processes available to fully kinetic models. Traditionally, empirical closure relations are used to close the moment-based system of equations, which typically approximate the pressure tensor or heat flux. The more accurate the closure relation, the stronger the simulation approaches kinetic-based results. In this paper, new closure terms are constructed using machine learning techniques. Two different machine learning models, a multi-layer perceptron and a gradient boosting regressor, synthesize a local closure relation for the pressure tensor and heat flux vector from fully kinetic simulations of a 2D magnetic reconnection problem. The models are compared to an existing closure relation for the pressure tensor, and the applicability of the models is discussed. The initial results show that the models can capture the diagonal components of the pressure tensor accurately, and show promising results for the heat flux, opening the way for new experiments in multi-scale modeling. We find that the sampling of the points used to train both models play a capital role in their accuracy.

arXiv comment37 pages, 12 figures, 2 tables

References in corpus (14)

• An overview of gradient descent optimization algorithms
• Machine learning and the physical sciences
• The Challenge of Machine Learning in Space Weather Nowcasting and Forecasting
• Discovery of Physics from Data: Universal Laws and Discrepancies
• 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
• Electromagnetic Energy Conversion in Downstream Fronts from 3D Kinetic Reconnection
• Deep Learning Models for Global Coordinate Transformations that Linearize PDEs
• Machine Learning Surrogate Models for Landau Fluid Closure
• Electron-scale reduced fluid models with gyroviscous effects
• Fluid moment hierarchy equations derived from gauge invariant quantum kinetic theory
• Neural network representability of fully ionized plasma fluid model closures
• Turbulence model reduction by deep learning
• Artificial neural network subgrid models of 2-D compressible magnetohydrodynamic turbulence

Cited by in corpus (9)

• Quantifying Energy Conversion in Higher Order Phase Space Density Moments in Plasmas
• Data-driven modeling of Landau damping by physics-informed neural networks
• Machine-learning heat flux closure for multi-moment fluid modeling of nonlinear Landau damping
• Electron cyclotron drift instability and anomalous transport: two-fluid moment theory and modeling
• Surrogate Modeling of Landau Damping with Deep Operator Networks
• Electron neural closure for turbulent magnetosheath simulations: energy channels
• Embedding physical symmetries into machine-learned reduced plasma physics models via data augmentation
• The role of field correlations on turbulent dissipation
• The Machine Learning Approach to Moment Closure Relations for Plasma: A Review