Technology Category
Machine Learning: Feature Construction/ReformulationKnowledge Representation and Reasoning: Geometric, Spatial, and Temporal ReasoningNatural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
How does ion temperature gradient turbulence depend on magnetic geometry? Insights from data and machine learning
🤖 AI Summary
This study investigates the regulation mechanisms of non-axisymmetric magnetic geometry on ion temperature gradient (ITG) turbulence-driven heat transport in fusion plasmas.
Method: Leveraging over 200,000 nonlinear gyrokinetic simulations—spanning optimized and randomly generated stellarator equilibria—we develop a physics-informed machine learning framework integrating convolutional neural networks (CNNs), decision trees, Spearman correlation analysis, sequential feature selection, and SHAP-based interpretability.
Contribution/Results: We identify, for the first time via data-driven analysis, flux-surface compression ratio and geodesic curvature as the dominant geometric regulators of ITG transport, thereby validating and extending existing theoretical proxy metrics. The CNN achieves high-accuracy heat-flux prediction on unseen configurations. We propose a translation-invariant feature parametrization paradigm. The complete dataset—including equilibrium configurations and simulation outputs—is publicly released to support future surrogate modeling efforts.
Technology Category
Application Category
📝 Abstract
Magnetic geometry has a significant effect on the level of turbulent transport in fusion plasmas. Here, we model and analyze this dependence using multiple machine learning methods and a dataset of>200,000 nonlinear simulations of ion-temperature-gradient turbulence in diverse non-axisymmetric geometries. The dataset is generated using a large collection of both optimized and randomly generated stellarator equilibria. At fixed gradients, the turbulent heat flux varies between geometries by several orders of magnitude. Trends are apparent among the configurations with particularly high or low heat flux. Regression and classification techniques from machine learning are then applied to extract patterns in the dataset. Due to a symmetry of the gyrokinetic equation, the heat flux and regressions thereof should be invariant to translations of the raw features in the parallel coordinate, similar to translation invariance in computer vision applications. Multiple regression models including convolutional neural networks (CNNs) and decision trees can achieve reasonable predictive power for the heat flux in held-out test configurations, with highest accuracy for the CNNs. Using Spearman correlation, sequential feature selection, and Shapley values to measure feature importance, it is consistently found that the most important geometric lever on the heat flux is the flux surface compression in regions of bad curvature. The second most important feature relates to the magnitude of geodesic curvature. These two features align remarkably with surrogates that have been proposed based on theory, while the methods here allow a natural extension to more features for increased accuracy. The dataset, released with this publication, may also be used to test other proposed surrogates, and we find many previously published proxies do correlate well with both the heat flux and stability boundary.
Problem
Research questions and friction points this paper is trying to address.
Analyzes ion temperature gradient turbulence dependency on magnetic geometry.
Uses machine learning to model turbulent heat flux in diverse geometries.
Identifies key geometric features affecting heat flux in fusion plasmas.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Machine learning analyzes turbulent transport
Convolutional neural networks predict heat flux
Dataset aids in testing theoretical surrogates
🔎 Similar Papers
No similar papers found.
