2026-06-22 バージニア工科大学（Virginia Tech）
＜関連情報＞
- https://news.vt.edu/articles/2026/06/science-modeling-nuclear-fusion-at-lightning-speed.html
- https://pubs.aip.org/aip/pop/article/33/6/063903/3395914/Machine-learning-for-electron-scale-turbulence
- https://www.nature.com/articles/s44286-026-00377-0
- https://www.sciencedirect.com/science/article/abs/pii/S0021999126000689
W7-Xにおける電子スケール乱流モデリングのための機械学習 Machine learning for electron-scale turbulence modeling in W7-X
Ionuţ-Gabriel Farcaş;Don Lawrence Carl Agapito Fernando;Alejandro Bañón Navarro;Gabriele Merlo;Frank Jenko
Physics of Plasmas Published:June 18 2026
DOI:https://doi.org/10.1063/5.0311057
FIG. 1.
Constructing reduced models for turbulent transport is essential for accelerating profile predictions and enabling many-query tasks such as parameter exploration, uncertainty quantification, and design optimization. This work investigates machine-learning-driven reduced models for electron temperature gradient (ETG) turbulence in the Wendelstein 7-X (W7-X) stellarator. We develop physics-guided scaling laws to predict the ETG heat flux at seven radial locations as functions of three key plasma parameters: the normalized ETG ( ), the ratio of normalized electron temperature and density gradients ( ), and the electron-to-ion temperature ratio ( ). The model coefficients are determined through regression combined with an active learning strategy. The procedure initializes the scaling laws using low-cardinality sparse-grid training data and iteratively enriches the training set by selecting maximally informative samples from an existing simulation database. The predictive performance of the models is assessed using out-of-sample datasets comprising more than 393 points per radial location. Using the coefficients identified at the seven training radial locations, we further derive regression-based parameterizations for the scaling-law coefficients as functions of radial position. The resulting models are then evaluated at three additional radial locations not used during training, including both interpolation and moderate extrapolation cases. Overall, our reduced models demonstrate good predictive performance and achieve accuracy comparable to the original reference simulations, including in interpolation and moderate extrapolation regimes. An important finding is that a single radius-independent model cannot adequately describe ETG transport across the W7-X core, suggesting the presence of geometry-dependent physics not captured by the present formulation.
複雑な物理現象を驚異的なスピードでシミュレーションする Simulating complex physics at lightning speed
Ionuț Farcaș & Karen Willcox
Nature Chemical Engineering Published:24 April 2026
DOI:https://doi.org/10.1038/s44286-026-00377-0
Ionuț Farcaș and Karen Willcox discuss how reduced-order models open new paths for simulating complex physics by compressing days of computation into seconds.
疎格子加速最適化動的モード分解によるプラズマ不安定性の高速予測 Fast prediction of plasma instabilities with sparse-grid-accelerated optimized dynamic mode decomposition
Kevin Gill, Ionuţ-Gabriel Farcaş, Silke Glas, Benjamin J. Faber
Journal of Computational Physics Available online: 29 January 2026
DOI:https://doi.org/10.1016/j.jcp.2026.114718
Abstract
Parametric data-driven reduced-order models (ROMs) that embed dependencies in a large number of input parameters are crucial for enabling many-query tasks in large-scale problems. These tasks, including design optimization, control, and uncertainty quantification, are essential for developing digital twins in real-world applications. However, standard grid-based data generation methods are computationally prohibitive due to the curse of dimensionality, as their cost scales exponentially with the number of inputs. This paper investigates efficient training of parametric data-driven ROMs using sparse grid interpolation with (L)-Leja points, specifically targeting scenarios with higher-dimensional input parameter spaces. (L)-Leja points are nested and exhibit slow growth, resulting in sparse grids with low cardinality in low-to-medium dimensional settings, making them ideal for large-scale, computationally expensive problems. Focusing on gyrokinetic simulations of plasma micro-instabilities in fusion experiments as a representative real-world application, we construct parametric ROMs for the full 5D gyrokinetic distribution function via optimized dynamic mode decomposition (optDMD) and sparse grids based on (L)-Leja points. We perform detailed experiments in two scenarios: First, the Cyclone Base Case benchmark assesses optDMD ROM prediction capabilities beyond training time horizons and across variations in the binormal wave number. Second, for a real-world electron-temperature-gradient-driven micro-instability simulation with six input parameters, we demonstrate that a predictive parametric optDMD ROM that is up to three orders of magnitude cheaper to evaluate can be constructed using only 28 high-fidelity gyrokinetic simulations, enabled by the use of sparse grids. In the broader context of fusion research, these results demonstrate the potential of sparse grid-based parametric ROMs to enable otherwise intractable many-query tasks.
