Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows

We present a new data reconstruction method with supervised machine learning techniques inspired by super resolution and inbetweening to recover high-resolution turbulent flows from grossly coarse flow data in space and time. For the present machine-learning-based data reconstruction, we use the dow...

Full description

Saved in:
Bibliographic Details
Published in:Journal of fluid mechanics Vol. 909
Main Authors: Fukami, Kai, Fukagata, Koji, Taira, Kunihiko
Format: Journal Article
Language:English
Published: Cambridge, UK Cambridge University Press 25.02.2021
Subjects:
Artificial neural networks
Channel flow
Computational fluid dynamics
Computer applications
Correlation coefficient
Correlation coefficients
Cylinders
Data
Direct numerical simulation
Evolution
Fluid dynamics
Fluid flow
Isotropic turbulence
JFM Papers
Learning algorithms
Machine learning
Mathematical models
Neural networks
Reconstruction
Resolution
Robustness (mathematics)
Three dimensional flow
Three dimensional models
Training
Turbulence
Turbulent flow
Two dimensional models
computational methods
turbulence simulation
ISSN:0022-1120, 1469-7645
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a new data reconstruction method with supervised machine learning techniques inspired by super resolution and inbetweening to recover high-resolution turbulent flows from grossly coarse flow data in space and time. For the present machine-learning-based data reconstruction, we use the downsampled skip-connection/multiscale model based on a convolutional neural network, incorporating the multiscale nature of fluid flows into its network structure. As an initial example, the model is applied to the two-dimensional cylinder wake at $Re_D = 100$. The reconstructed flow fields by the present method show great agreement with the reference data obtained by direct numerical simulation. Next, we apply the current model to a two-dimensional decaying homogeneous isotropic turbulence. The machine-learned model is able to track the decaying evolution from spatial and temporal coarse input data. The proposed concept is further applied to a complex turbulent channel flow over a three-dimensional domain at $Re_{\tau }=180$. The present model reconstructs high-resolved turbulent flows from very coarse input data in space, and also reproduces the temporal evolution for appropriately chosen time interval. The dependence on the number of training snapshots and duration between the first and last frames based on a temporal two-point correlation coefficient are also assessed to reveal the capability and robustness of spatio-temporal super resolution reconstruction. These results suggest that the present method can perform a range of flow reconstructions in support of computational and experimental efforts.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0022-1120
1469-7645
DOI:10.1017/jfm.2020.948