Towards Fast and Accurate Predictions of Radio Frequency Power Deposition and Current Profile via Data-driven Modeling

Abstract

Three machine learning techniques (multilayer perceptron, random forest, and Gaussian process) provide fast surrogate models for lower hybrid current drive (LHCD) simulations. A single GENRAY/CQL3D simulation without radial diffusion of fast elec- trons requires several minutes of wall-clock time to complete, which is acceptable for many purposes, but too slow for integrated modeling and real-time control applications. The machine learning models use a database of 16,000+ GENRAY/CQL3D simulations for training, validation, and testing. Latin hypercube sampling methods ensure that the database covers the range of 9 input parameters (ne0, Te0, Ip, Bt, R0, n||, Zeff , Vloop, PLHCD) with sufficient density in all regions of parameter space. The surrogate models reduce the inference time from minutes to ∼ms with high accuracy across the input parameter space.