Accelerated Bayesian inference of plasma profiles with self-consistent MHD equilibria at W7-X via neural networks

Abstract

High-β operations require a fast and robust inference of plasma parameters with a self-consistent magnetohydrodynamic (MHD) equilibrium. Precalculated MHD equilibria are usually employed at Wendelstein 7-X (W7-X) due to the high computational cost. To address this, we couple a physics-regularizedartificial neural network (NN) model that approximates the ideal-MHD equilibrium with the Bayesianmodeling framework Minerva. We show the fast and robust inference of plasma profiles (electron temperature and density) with a self-consistent MHD equilibrium approximated by the NN model. Weinvestigate the robustness of the inference across diverse synthetic W7-X plasma scenarios. The inferredplasma parameters and their uncertainties are compatible with the parameters inferred using the variational moments equilibrium code (VMEC), and the inference time is reduced by more than two ordersof magnitude. This work suggests that MHD self-consistent inferences of plasma parameters can beperformed between shots.