Neural network surrogate of QuaLiKiz using JET experimental data to populate training space

Abstract

Within integrated tokamak plasma modelling, turbulent transport codes are typically the computational bottleneck limiting their routine use outside of post-discharge analysis. Neural network (NN) surrogates have been used to accelerate these calculations while retaining the desired accuracy of the physics-based models. This paper extends a previous NN model, known as QLKNN-hyper-10D, by incorporating the impact of impurities, plasma rotation and magnetic equilibrium effects. This is achieved by adding a light impurity fractional density ($n_{imp,light}/n_e$) and its normalized gradient, the normalized pressure gradient ($\alpha$), the toroidal Mach number ($M_{tor}$) and the normalized toroidal flow velocity gradient. The input space was sampled based on experimental data from the JET tokamak to avoid the curse of dimensionality. The resulting networks, named QLKNN-jetexp-15D, show good agreement with the original QuaLiKiz model, both by comparing individual transport quantity predictions as well as comparing its impact within the integrated model, JINTRAC. The profile-averaged RMS of the integrated modelling simulations is <10% for each of the 5 scenarios tested. This is non-trivial given the potential numerical instabilities present within the highly nonlinear system of equations governing plasma transport, especially considering the novel addition of momentum flux predictions to the model proposed here. An evaluation of all 25 NN output quantities at one radial location takes $\sim$0.1 ms, $10^4$ times faster than the original QuaLiKiz model. Within the JINTRAC integrated modelling tests performed in this study, using QLKNN-jetexp-15D resulted in a speed increase of only 60 - 100 as other physics modules outside of turbulent transport become the bottleneck.

arXiv comment34 pages, 24 figures, Physics of Plasmas

References in corpus (8)

• Deep Learning in Neural Networks: An Overview
• Fast modeling of turbulent transport in fusion plasmas using neural networks
• Tractable flux-driven temperature, density, and rotation profile evolution with the quasilinear gyrokinetic transport model QuaLiKiz
• Real-time capable first principle based modelling of tokamak turbulent transport
• Application of Gaussian process regression to plasma turbulent transport model validation via integrated modelling
• Evaluation of the Dreicer runaway generation rate in the presence of high-Z impurities using a neural network
• First-principles-based multiple-isotope particle transport modelling at JET
• Flux-driven integrated modelling of main ion pressure and trace tungsten transport in ASDEX Upgrade

Cited by in corpus (8)

• 2022 Review of Data-Driven Plasma Science
• Plasma Surrogate Modelling using Fourier Neural Operators
• Fast Dynamic 1D Simulation of Divertor Plasmas with Neural PDE Surrogates
• Two step clustering for data reduction combining DBSCAN and k-means clustering
• Proof of concept of a fast surrogate model of the VMEC code via neural networks in Wendelstein 7-X scenarios
• Fast transport simulations with higher-fidelity surrogate models for ITER
• EuroPED-NN: Uncertainty aware surrogate model
• Efficient dataset construction using active learning and uncertainty-aware neural networks for plasma turbulent transport surrogate models