Identification of high order closure terms from fully kinetic simulations using machine learning
This work addresses the challenge of improving multi-scale modeling in plasma physics, representing an incremental advance by applying existing machine learning methods to enhance closure relations.
The paper tackled the problem of approximating small-scale physics in fluid-based plasma simulations by constructing new closure terms for the pressure tensor and heat flux using machine learning from fully kinetic simulations, with initial results showing accurate capture of diagonal pressure tensor components and promising results for heat flux.
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.