刮离层等离子体模拟的概率与几何感知神经代理模型
Probabilistic and Geometry Aware Neural Surrogate of Scrape Off Layer Plasma Simulations
- Eindhoven University of Technology（埃因霍温理工大学）
- DIFFER（荷兰等离子体物理研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对托卡马克边界等离子体模拟，提出将曲线网格展开为图像张量并采用条件流匹配模型，实现概率性代理，在敏感工作点捕获多种结果而非平均。
AI中文摘要：
托卡马克边界等离子体模拟的快速代理模型通常是确定性回归器，将全局工作点映射为扁平化的单元值向量。在偏滤器脱离转变附近，稳态并非可靠地单值。点估计必须对性质不同的等离子体状态进行平均，且不附带置信度说明。此外，扁平化向量表示丢弃了SOLPS-ITER网格的几何结构。本工作同时解决这两个问题。我们将曲线网格展开为三个固定大小的图像张量，其布局保留单元邻接关系并可精确反转，使卷积网络能够在几何上作用而不损失信息。随后，一种非常适合高敏感系统的条件流匹配模型在此表示上进行训练。结果是高效、可扩展的代理模型，即使在敏感工作点也能捕获多种合理结果。在气体喷注扫描中，预测分布在早期状态转变处分裂为热模式和冷模式。对注入已知大小分叉的合成数据的进一步检查确认，模型恢复两个分支而非其平均值。
英文摘要：
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.
