Super-resolution reconstruction of turbulent flow fields at various Reynolds numbers based on generative adversarial networks

This study presents a deep learning-based framework to recover high-resolution turbulent velocity fields from extremely low-resolution data at various Reynolds numbers by utilizing the concept of generative adversarial networks. A multiscale enhanced super-resolution generative adversarial network is applied as a model to reconstruct the high-resolution velocity fields, and direct numerical simulation data of turbulent channel flow with large longitudinal ribs at various Reynolds numbers are used to evaluate the performance of the model. The model is found to have the capacity to accurately reconstruct the high-resolution velocity fields from data at two different down-sampling factors in terms of the instantaneous velocity fields, two-point correlations, and turbulence statistics. The results further reveal that the model is able to reconstruct high-resolution velocity fields at Reynolds numbers that fall within the range of the training Reynolds numbers. (C) 2022 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

Automated summary

This study presents a deep learning-based framework that utilizes the concept of generative adversarial networks to recover high-resolution turbulent velocity fields from extremely low-resolution data. The model, a multiscale enhanced super-resolution generative adversarial network, accurately reconstructs high-resolution velocity fields, as demonstrated by evaluating its performance using direct numerical simulation data. The results show that the model is capable of reconstructing high-resolution velocity fields at different down-sampling factors and within the range of the training Reynolds numbers.