Fast transport simulations with higher-fidelity surrogate models for ITER

Abstract

A fast and accurate turbulence transport model based on quasilinear gyrokinetics is developed. The model consists of a set of neural networks trained on a bespoke quasilinear GENE dataset, with a saturation rule calibrated to dedicated nonlinear simulations. The resultant neural network is approximately eight orders of magnitude faster than the original GENE quasilinear calculations. ITER predictions with the new model project a fusion gain in line with ITER targets. While the dataset is currently limited to the ITER baseline regime, this approach illustrates a pathway to develop reduced-order turbulence models both faster and more accurate than the current state-of-the-art.

References in corpus (8)

• Nonlinear stabilization of tokamak microturbulence by fast ions
• Fast modeling of turbulent transport in fusion plasmas using neural networks
• Electromagnetic stabilization of tokamak microturbulence in a high-$\beta$ regime
• 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
• Neural network surrogate of QuaLiKiz using JET experimental data to populate training space
• Comparison between measured and predicted turbulence frequency spectra in ITG and TEM regimes
• Proof of concept of a fast surrogate model of the VMEC code via neural networks in Wendelstein 7-X scenarios

Cited by in corpus (2)

• A quasi-linear model of electromagnetic turbulent transport and its application to flux-driven transport predictions for STEP
• Efficient dataset construction using active learning and uncertainty-aware neural networks for plasma turbulent transport surrogate models