Magnetohydrodynamics with physics informed neural operators
Magnetohydrodynamics with physics informed neural operators
复制标题
DOI：
10.1088/2632-2153/ace30a
复制
发表时间：
2023-02
期刊：
影响因子：
--
通讯作者：
S. Rosofsky;E. Huerta
中科院分区：
文献类型：
--
作者：
S. Rosofsky;E. Huerta
多尺度和多物理复杂系统的建模通常涉及使用可以最佳利用极端规模计算的科学软件。尽管近年来取得了重大进展，但这些模拟仍然是计算密集型且耗时的。在这里，我们探索使用人工智能来加速复杂系统的建模，而计算成本仅为经典方法的一小部分，并首次应用物理通知神经算子 (NO) (PINO) 来模拟二维不可压缩磁流体动力学 (MHD) 模拟。我们的 AI 模型采用张量傅里叶 NO 作为其骨干，我们使用 TensorLY 包实现。我们的结果表明，PINO 可以准确地捕捉 MHD 模拟的物理现象，用雷诺数 Re⩽250 描述层流。我们还探索了 AI 替代物对湍流的适用性，并讨论了可能纳入未来工作中的各种方法，以创建 AI 模型，为各种雷诺数提供计算高效且高保真度的 MHD 模拟描述。本项目开发的科学软件随本手稿一起发布。
The modeling of multi-scale and multi-physics complex systems typically involves the use of scientific software that can optimally leverage extreme scale computing. Despite major developments in recent years, these simulations continue to be computationally intensive and time consuming. Here we explore the use of AI to accelerate the modeling of complex systems at a fraction of the computational cost of classical methods, and present the first application of physics informed neural operators (NOs) (PINOs) to model 2D incompressible magnetohydrodynamics (MHD) simulations. Our AI models incorporate tensor Fourier NOs as their backbone, which we implemented with the TensorLY package. Our results indicate that PINOs can accurately capture the physics of MHD simulations that describe laminar flows with Reynolds numbers Re⩽250 . We also explore the applicability of our AI surrogates for turbulent flows, and discuss a variety of methodologies that may be incorporated in future work to create AI models that provide a computationally efficient and high fidelity description of MHD simulations for a broad range of Reynolds numbers. The scientific software developed in this project is released with this manuscript.