Physics-regularized neural network of the ideal-MHD solution operator in Wendelstein 7-X configurations

Abstract

The stellarator is a promising concept to produce energy from nuclear fusion by magnetically confining a high-pressure plasma. In a stellarator, the confining field is three-dimensional, and the computational cost of solving the 3D magnetohydrodynamic (MHD) equations currently limits stellarator research and design. Although data-driven approaches have been proposed to provide fast 3D MHD equilibria, the accuracy with which equilibrium properties are reconstructed is unknown. In this work, we describe an artificial neural network (NN) that quickly approximates the ideal-MHD solution operator in Wendelstein 7-X (W7-X) configurations. This model fulfils equilibrium symmetries by construction. The MHD force residual regularizes the solution of the NN to satisfy the ideal-MHD equations. The model predicts the equilibrium solution with high accuracy, and it faithfully reconstructs global equilibrium quantities and proxy functions used in stellarator optimization. The regularization term enforces that the NN reduces the ideal-MHD force residual, and solutions that are better than ground truth equilibria can be obtained at inference time. We also optimize W7-X magnetic configurations, where desiderable configurations can be found in terms of fast particle confinement. This work demonstrates with which accuracy NN models can approximate the 3D ideal-MHD solution operator and reconstruct equilibrium properties of interest, and it suggests how they might be used to optimize stellarator magnetic configurations.