Deep learning methods for super-resolution reconstruction of turbulent flows

By Bo Liu, Jiupeng Tang, Haibo Huang, Xi-yun Lu. The Physics of Fluids, 2020

357 citations recorded by the source corpus.

Two deep learning (DL) models addressing the super-resolution (SR) reconstruction of turbulent flows from low-resolution coarse flow field data are developed. One is the static convolutional neural network (SCNN), and the other is the novel multiple temporal paths convolutional neural network (MTPC). The SCNN model takes instantaneous snapshots as an input, while the MTPC model takes a time series of velocity fields as an input, and it includes spatial and temporal information simultaneously. Three temporal paths are designed in the MTPC to fully capture features in different time ranges. A weight path is added to generate pixel-level weight maps of each temporal path. These models were first applied to forced isotropic turbulence. The corresponding high-resolution flow fields were reconstructed with high accuracy. The MTPC seems to be able to reproduce many important features as well, such as kinetic energy spectra and the joint probability density function of the second and third invariants of the velocity gradient tensor. As a further evaluation, the SR reconstruction of anisotropic channel flow with the DL models was performed. The SCNN and MTPC remarkably improve the spatial resolution in various wall regions and potentially grasp all the anisotropic turbulent properties. It is also shown that the MTPC supplements more under-resolved details than the SCNN. The success is attributed to the fact that the MTPC can extract extra temporal information from consecutive fluid fields. The present work may contribute to the development of the subgrid-scale model in computational fluid dynamics and enrich the application of SR technology in fluid mechanics.Two deep learning (DL) models addressing the super-resolution (SR) reconstruction of turbulent flows from low-resolution coarse flow field data are developed. One is the static convolutional neural network (SCNN), and the other is the novel multiple temporal paths convolutional neural network (MTPC). The SCNN model takes instantaneous snapshots as an input, while the MTPC model takes a time series of velocity fields as an input, and it includes spatial and temporal information simultaneously. Three temporal paths are designed in the MTPC to fully capture features in different time ranges. A weight path is added to generate pixel-level weight maps of each temporal path. These models were first applied to forced isotropic turbulence. The corresponding high-resolution flow fields were reconstructed with high accuracy. The MTPC seems to be able to reproduce many important features as well, such as kinetic energy spectra and the joint probability density function of the second and third invariants of the veloc...

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/0d33aed5ff853e1438ca2cc706cf886a4a64be34

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

1. Sungjin Won
2. Junhyuk Kim
3. Hyojin Kim
4. Changhoon Lee

In Computer Vision and Pattern Recognition

1. Sungjin Won
2. Junhyuk Kim
3. Hyojin Kim
4. Changhoon Lee

In Statistical and Nonlinear Physics

1. Sungjin Won
2. Junhyuk Kim
3. Hyojin Kim
4. Changhoon Lee

Citations in the corpus

• Unsupervised deep learning for super-resolution reconstruction of turbulence (2020, methodology): “Both Fukami et al. (2019) and Liu et al. (2020) trained CNNs in the direction of reducing the mean-squared error (MSE) of target quantities between prediction and true data.”