Improved super-resolution reconstruction of turbulent flows with spectral loss function
Physics of Fluids · 01.03.2025 · 37 (3)
DOI: 10.1063/5.0258090 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physics of Fluids, online erschienen am 27.03.2025. Verfasst von Ruyue Cheng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: China Scholarship Council, Deutsche Forschungsgemeinschaft, Baden-Württemberg Supercomputing Resources.
Abstract (Originalsprache)
Super-resolution (SR) reconstruction of turbulent flows, inspired by breakthroughs in image SR, aims to generate high-resolution flow fields from low-resolution data that are available from numerical simulations and experimental measurements. Deep convolutional neural networks (CNN) have long been the pillar in both image and turbulence SR. Recently, networks based on the Swin Transformer featuring an innovative attention mechanism have achieved great success in image SR. This study first applies a latest variant of the Swin Transformer, SwinFIR (Image Restoration with Swin Transformer using a fast Fourier convolution layer), to the super-resolution of forced homogeneous isotropic turbulence, and compares its performance with a well-established CNN-based model, the Residual-in-Residual Dense Block (RRDB). The results show that the SwinFIR slightly outperforms the RRDB after being trained with a Ln-norm-based pixel loss, but both models still significantly underestimate the high-frequency turbulent energy. Further improvement is hindered by the loss. To address this issue, a new fine-tuning strategy featuring a spectral loss is proposed in this work. The results show that the proposed fine-tuning strategy is highly effective in improving the reconstruction of high-frequency turbulence. The generalization tests on data with higher Reynolds numbers unseen in the training further demonstrate that the fine-tuned network generalizes well for 4× SR (i.e., enhancing resolution by a factor of four in each direction), and that good generalization performance can also be achieved for higher SR factors with a consistent ratio of grid size to Kolmogorov length scale. The underlying mechanisms dictating the generalization performance are discussed, providing clues for developing better training strategies that can endow models with unconditional generalization capability.
Förderung
- China Scholarship Council
- Deutsche Forschungsgemeinschaft
- Baden-Württemberg Supercomputing Resources
Zitieren
APA
Cheng, R., Shamooni, A., Zirwes, T., & Kronenburg, A. (2025). Improved super-resolution reconstruction of turbulent flows with spectral loss function. Physics of Fluids, 37(3). https://doi.org/10.1063/5.0258090
Vancouver
Cheng R, Shamooni A, Zirwes T, Kronenburg A. Improved super-resolution reconstruction of turbulent flows with spectral loss function. Physics of Fluids. 2025;37(3). doi:10.1063/5.0258090
BibTeX
@article{Cheng2025,
author = {Cheng, Ruyue and Shamooni, Ali and Zirwes, Thorsten and Kronenburg, Andreas},
title = {Improved super-resolution reconstruction of turbulent flows with spectral loss function},
journal = {Physics of Fluids},
year = {2025},
volume = {37},
number = {3},
doi = {10.1063/5.0258090}
}
EUVIMED