Artificial neural network subgrid models of 2D compressible magnetohydrodynamic turbulence
Artificial neural network subgrid models of 2D compressible magnetohydrodynamic turbulence
复制标题
DOI：
10.1103/physrevd.101.084024
复制
发表时间：
2019-12
影响因子：
5
通讯作者：
S. Rosofsky;E. Huerta
中科院分区：
文献类型：
--
作者：
S. Rosofsky;E. Huerta
我们探索了深度学习的适用性，以捕获磁化Kelvin-Helmholtz不稳定性的2D模拟的亚网格尺度理想磁流体力学湍流的物理学。我们以不同的分辨率进行模拟，系统地量化神经网络模型的性能，以再现这些复杂模拟的物理特性。我们比较我们的神经网络的性能与梯度模型，这是广泛使用的磁流体动力学文献。我们的研究结果表明，神经网络显着优于梯度模型在准确计算亚网格尺度张量编码的磁流体动力学湍流的影响。据我们所知，这是第一次探索性研究使用深度学习来学习和再现磁流体力学湍流的物理学。
We explore the suitability of deep learning to capture the physics of subgrid-scale ideal magnetohydrodynamics turbulence of 2D simulations of the magnetized Kelvin-Helmholtz instability. We produce simulations at different resolutions to systematically quantify the performance of neural network models to reproduce the physics of these complex simulations. We compare the performance of our neural networks with gradient models, which are extensively used in the magnetohydrodynamic literature. Our findings indicate that neural networks significantly outperform gradient models in accurately computing the subgrid-scale tensors that encode the effects of magnetohydrodynamics turbulence. To the best of our knowledge, this is the first exploratory study on the use of deep learning to learn and reproduce the physics of magnetohydrodynamics turbulence.