Probabilistic and Geometry Aware Neural Surrogate of Scrape Off Layer Plasma Simulations

2026-09-23

AI Summary

本文针对托卡马克边界等离子体模拟中的不确定性问题，通过将弯曲网格展开为固定大小的图像张量并使用条件流匹配模型进行训练，提出了一个能够捕捉多种可能结果的概率性几何感知神经代理模型。

Abstract

Fast surrogates for tokamak boundary-plasma simulation are typically deterministic regressors mapping a global operating point to a flattened vector of cell values. Near the divertor detachment transition the steady state is not reliably single-valued. A point estimate must average over qualitatively different plasma states, and it arrives with no statement of confidence. Moreover, the flattened vector representation discards the geometric structure of the SOLPS-ITER mesh. This work addresses both problems. We unroll the curvilinear mesh into three fixed-size image tensors whose layout preserves cell adjacency and inverts exactly, letting a convolutional network act on the geometry without loss of information. A conditional flow matching model, well suited to highly sensitive systems, is then trained on this representation. The result is an efficient, scalable surrogate that captures multiple plausible outcomes even at sensitive operating points. Along a gas-puff scan, the predictive distribution splits into a hot and a cold mode across an early regime transition. A further check on synthetic data with an injected bifurcation of known size confirms the model recovers both branches rather than their average.

Problem

• tokamak boundary-plasma
• divertor detachment transition
• steady state
• geometric structure
• SOLPS-ITER mesh

Innovation

• curvilinear mesh
• convolutional network
• conditional flow matching