Learning the dynamics of a one-dimensional plasma model with graph neural networks

Abstract

We explore the possibility of fully replacing a plasma physics kinetic simulator with a graph neural network-based simulator. We focus on this class of surrogate models given the similarity between their message-passing update mechanism and the traditional physics solver update, and the possibility of enforcing known physical priors into the graph construction and update. We show that our model learns the kinetic plasma dynamics of the one-dimensional plasma model, a predecessor of contemporary kinetic plasma simulation codes, and recovers a wide range of well-known kinetic plasma processes, including plasma thermalization, electrostatic fluctuations about thermal equilibrium, and the drag on a fast sheet and Landau damping. We compare the performance against the original plasma model in terms of run-time, conservation laws, and temporal evolution of key physical quantities. The limitations of the model are presented and possible directions for higher-dimensional surrogate models for kinetic plasmas are discussed.

arXiv commenttitle changed, accepted for publication in Machine Learning: Science and Technology, code available at https://github.com/diogodcarvalho/gns-sheet-model

References in corpus (12)

• Array Programming with NumPy
• Fourier Neural Operator for Parametric Partial Differential Equations
• Learning to Simulate Complex Physics with Graph Networks
• Nuclear reaction rates and energy in stellar plasmas : The effect of highly damped modes
• Data-driven discovery of reduced plasma physics models from fully-kinetic simulations
• Message Passing Neural PDE Solvers
• Decomposition of Plasma Kinetic Entropy into Position and Velocity Space and the Use of Kinetic Entropy in Particle-in-Cell Simulations
• Unsupervised Discovery of Inertial-Fusion Plasma Physics using Differentiable Kinetic Simulations and a Maximum Entropy Loss Function
• Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics
• Machine Learning-based models in particle-in-cell codes for advanced physics extensions
• Learning rigid dynamics with face interaction graph networks
• Modeling of a Liquid Leaf Target TNSA Experiment using Particle-In-Cell Simulations and Deep Learning

Cited by in corpus (1)

• Embedding physical symmetries into machine-learned reduced plasma physics models via data augmentation