Unsupervised deep learning for super-resolution reconstruction of turbulence

By Hyojin Kim, Junhyuk Kim, Sungjin Won, Changhoon Lee. Journal of Fluid Mechanics, 2020

304 citations recorded by the source corpus.

Abstract Recent attempts to use deep learning for super-resolution reconstruction of turbulent flows have used supervised learning, which requires paired data for training. This limitation hinders more practical applications of super-resolution reconstruction. Therefore, we present an unsupervised learning model that adopts a cycle-consistent generative adversarial network (CycleGAN) that can be trained with unpaired turbulence data for super-resolution reconstruction. Our model is validated using three examples: (i) recovering the original flow field from filtered data using direct numerical simulation (DNS) of homogeneous isotropic turbulence; (ii) reconstructing full-resolution fields using partially measured data from the DNS of turbulent channel flows; and (iii) generating a DNS-resolution flow field from large-eddy simulation (LES) data for turbulent channel flows. In examples (i) and (ii), for which paired data are available for supervised learning, our unsupervised model demonstrates qualitatively and quantitatively similar performance as that of the best supervised learning model. More importantly, in example (iii), where supervised learning is impossible, our model successfully reconstructs the high-resolution flow field of statistical DNS quality from the LES data. Furthermore, we find that the present model has almost universal applicability to all values of Reynolds numbers within the tested range. This demonstrates that unsupervised learning of turbulence data is indeed possible, opening a new door for the wide application of super-resolution reconstruction of turbulent fields.

Subfields: Atomic and Molecular Physics, and Optics, Computational Mechanics, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/7614bce18df2de3bc0039cd68594b2b8c601da73

How researchers see this paper

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

In Atomic and Molecular Physics, and Optics

In Computational Mechanics

In Statistical and Nonlinear Physics

Citations in the corpus

A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction (2022, methodology): “To address the case where low and high-resolution ﬂow ﬁelds are not matched, Kim et al. 49 proposed a CycleGAN 50 -based model trained with unpaired turbulence data for super-resolution.”
Enhancing computational fluid dynamics with machine learning (2021, background): “…to the work by Guastoni et al. [137], there are a number of studies documenting the possibility of performing super-resolution predictions ( e.g. when limited ﬂow information is available) in wall-bounded turbulence using CNNs, autoencoders and generative-adversarial networks (GANs) [138–141].”