Super-resolution reconstruction of turbulent flows with machine learning

By Kai Fukami, Koji Fukagata, Kunihiko Taira. Journal of Fluid Mechanics, 2018

788 citations recorded by the source corpus.

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.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a0390b8d4a82daa1d24bba341b317aa710e4ce4d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers (2020, background): “The potential null-space of T T is an interesting topic for super-resolution approaches [15].”
Deep learning methods for super-resolution reconstruction of turbulent flows (2020, methodology): “Fukaimi et al. 23 proposed a hybrid Downsam-pled Skip-Connection Multi-Scale (DSC/MS) model to reconstruct the flow field of two-dimensional decaying isotropic turbulence.”
Machine Learning for Fluid Mechanics (2019, background): “Recently Fukami et al. (2018) have developed a CNN-based super-resolution algorithm and demonstrated its eﬀectiveness on turbulent ﬂow reconstruction, showing that the energy spectrum is accurately preserved.”