Fast modeling of turbulent transport in fusion plasmas using neural networks
arXiv:1911.05617 · doi:10.1063/1.5134126
Abstract
We present an ultrafast neural network (NN) model, QLKNN, which predicts core tokamak transport heat and particle fluxes. QLKNN is a surrogate model based on a database of 300 million flux calculations of the quasilinear gyrokinetic transport model QuaLiKiz. The database covers a wide range of realistic tokamak core parameters. Physical features such as the existence of a critical gradient for the onset of turbulent transport were integrated into the neural network training methodology. We have coupled QLKNN to the tokamak modelling framework JINTRAC and rapid control-oriented tokamak transport solver RAPTOR. The coupled frameworks are demonstrated and validated through application to three JET shots covering a representative spread of H-mode operating space, predicting turbulent transport of energy and particles in the plasma core. JINTRAC-QLKNN and RAPTOR-QLKNN are able to accurately reproduce JINTRAC-QuaLiKiz T i,e and n e profiles, but 3 to 5 orders of magnitude faster. Simulations which take hours are reduced down to only a few tens of seconds. The discrepancy in the final source-driven predicted profiles between QLKNN and QuaLiKiz is on the order 1%-15%. Also the dynamic behaviour was well captured by QLKNN, with differences of only 4%-10% compared to JINTRAC-QuaLiKiz observed at mid-radius, for a study of density buildup following the L-H transition. Deployment of neural network surrogate models in multi-physics integrated tokamak modelling is a promising route towards enabling accurate and fast tokamak scenario optimization, Uncertainty Quantification, and control applications.
arXiv comment18 pages, 11 figures, Physics of Plasmas, ICDDPS 2019 conference paper
References in corpus (9)
- The NumPy array: a structure for efficient numerical computation
- 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
- Comparison between measured and predicted turbulence frequency spectra in ITG and TEM regimes
- Angular momentum transport modeling: achievements of a gyrokinetic quasi-linear approach
- 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 (16)
- The data-driven future of high energy density physics
- Fast modeling of turbulent transport in fusion plasmas using neural networks
- Physics-constrained, low-dimensional models for MHD: First-principles and data-driven approaches
- 2022 Review of Data-Driven Plasma Science
- Plasma Surrogate Modelling using Fourier Neural Operators
- Neural network surrogate of QuaLiKiz using JET experimental data to populate training space
- A machine-learning-based tool for last closed-flux surface reconstruction on tokamaks
- 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
- Using HPC infrastructures for deep learning applications in fusion research
- How does ion temperature gradient turbulence depend on magnetic geometry? Insights from data and machine learning
- Uncertainty Quantification of Surrogate Models using Conformal Prediction
- EuroPED-NN: Uncertainty aware surrogate model
- Fast prediction of plasma instabilities with sparse-grid-accelerated optimized dynamic mode decomposition
- Efficient dataset construction using active learning and uncertainty-aware neural networks for plasma turbulent transport surrogate models