Super-resolution reconstruction of turbulent flows with machine learning
Super-resolution reconstruction of turbulent flows with machine learning
复制标题
DOI：
10.1017/jfm.2019.238
复制
发表时间：
2019-07-10
影响因子：
3.7
通讯作者：
Taira, Kunihiko
中科院分区：
文献类型：
--
作者：
Fukami, Kai;Fukagata, Koji;Taira, Kunihiko
我们使用机器学习对严重欠分辨的湍流场数据进行超分辨率分析，以重建高分辨率流场。开发了两种机器学习模型，即卷积神经网络（CNN）和混合下采样跳跃连接/多尺度（DSC/MS）模型。这些机器学习模型应用于二维圆柱尾迹作为初步测试，并显示出显着的能力，重建层流从低分辨率流场数据。我们进一步评估这些模型的二维均匀湍流的性能。CNN和DSC/MS模型被发现可以从非常粗糙的流场图像中以显着的精度重建湍流。对于湍流问题，基于机器学习的超分辨率分析可以大大提高空间分辨率，只需50个训练快照数据，具有揭示复杂湍流亚网格物理的巨大潜力。随着越来越多的流场数据从高保真模拟和实验，本方法激励有效的超分辨率模型的各种流体流动的发展。
We use machine learning to perform super-resolution analysis of grossly under-resolved turbulent flow field data to reconstruct the high-resolution flow field. Two machine learning models are developed, namely, the convolutional neural network (CNN) and the hybrid downsampled skip-connection/multi-scale (DSC/MS) models. These machine learning models are applied to a two-dimensional cylinder wake as a preliminary test and show remarkable ability to reconstruct laminar flow from low-resolution flow field data. We further assess the performance of these models for two-dimensional homogeneous turbulence. The CNN and DSC/MS models are found to reconstruct turbulent flows from extremely coarse flow field images with remarkable accuracy. For the turbulent flow problem, the machine-leaning-based super-resolution analysis can greatly enhance the spatial resolution with as little as 50 training snapshot data, holding great potential to reveal subgrid-scale physics of complex turbulent flows. With the growing availability of flow field data from high-fidelity simulations and experiments, the present approach motivates the development of effective super-resolution models for a variety of fluid flows.