发表机构
Canadian Institute for Theoretical Astrophysics; University of Toronto; Purdue University; University of Maryland, College Park; Flatiron Institute（加拿大理论天体物理研究所; 多伦多大学; 普渡大学; 马里兰大学帕克分校; 熨斗研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
PHASE通过结合迁移学习、机制感知自适应和残差校正，用单一模型实现跨参数不可压缩MHD的精确预测，大幅降低误差并泛化到未见参数。
AI 中文摘要
磁流体动力学（MHD）在天体物理学、空间科学、聚变和工程中的等离子体建模中至关重要，但解析多尺度MHD动力学在计算上代价高昂。机器学习代理通过学习可复用的解算子实现快速推理，然而现有模型需要对每个物理机制进行单独训练，限制了在变化参数设置下的泛化能力。我们提出PHASE，一种具有残差误差校正的物理自适应可扩展算子，旨在用单一模型对变化物理参数下的不可压缩MHD进行建模。PHASE结合了迁移学习、机制感知自适应、物理中心学习和残差细化，以提高跨MHD机制的物理保真度和泛化能力。这些改进共同在二维MHD湍流上实现了最先进的预测精度，将物理场上的相对$L_2$误差比之前的MHD神经算子基线降低了一个数量级以上。此外，PHASE无需重新训练即可成功泛化到未见过的参数值，展示了算子学习所期望的跨机制适应性。我们使用导出的物理场、谱分析和分布统计对PHASE进行评估，而不仅仅是逐点预测误差，一致观察到物理保真度的提高。我们还通过在Kelvin-Helmholtz不稳定性上进行测试，进一步展示了我们的框架能够准确模拟MHD不稳定性，证明了我们方法的鲁棒性。
英文摘要
Magnetohydrodynamics (MHD) is central to plasma modeling in astrophysics, space science, fusion, and engineering, but resolving multiscale MHD dynamics is computationally expensive. Machine-learning surrogates enable fast inference by learning reusable solution operators, yet existing models require separate training for each physical regime, limiting generalization across varying parameter settings. We introduce PHASE, a PHysics-Adaptive Scalable operator with residual Error correction, designed to model incompressible MHD across varying physical parameters with a single model. PHASE combines transfer learning, regime-aware adaptation, physics-centered learning, and residual refinement to improve both physical fidelity and generalization across MHD regimes. Together, these improvements achieve state-of-the-art prediction accuracy on two-dimensional MHD turbulence by reducing relative $L_2$ errors on physical fields by more than an order of magnitude compared to prior MHD neural-operator baselines. Moreover, PHASE generalizes successfully to unseen parameter values without retraining, demonstrating the cross-regime adaptability expected from operator learning. We evaluate PHASE beyond point-wise prediction errors using derived physical fields, spectral analysis, and distribution statistics, consistently observing improved physical fidelity. We further show that our framework can accurately simulate MHD instabilities by testing it on the Kelvin--Helmholtz instability, demonstrating the robustness of our method.
Comments22 pages, 13 figures
