Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers

TL;DR

This paper introduces a GAN-based unsupervised learning approach to generate realistic turbulent inflow conditions across various Reynolds numbers, capturing universal turbulence features and temporal dynamics.

Contribution

The study develops a novel RNN-GAN model that accurately generates time-varying turbulent flow fields, demonstrating the ability to learn universal turbulence characteristics from limited data.

Findings

GAN can generate turbulence fields similar to DNS data.

The model generalizes across multiple Reynolds numbers without retraining.

The RNN-GAN captures spatiotemporal correlations effectively.

Abstract

A realistic inflow boundary condition is essential for successful simulation of the developing turbulent boundary layer or channel flows. Recent advances in artificial intelligence (AI) have enabled the development of an inflow generator that performs better than the synthetic methods based on intuitions. In the present work, we applied generative adversarial networks (GANs), a representative of unsupervised learning, to generate an inlet boundary condition of turbulent channel flow. Upon learning the two-dimensional spatial structure of turbulence using data obtained from direct numerical simulation (DNS) of turbulent channel flow, the GAN could generate instantaneous flow fields that are statistically similar to those of DNS. Surprisingly, the GAN could produce fields at various Reynolds numbers without any additional simulation based on the trained data of only three Reynolds numbers. This indicates that the GAN could learn the universal nature of Reynolds number effect and might reflect other simulation conditions. Eventually, through a combination of the GAN and a recurrent neural network (RNN), we developed a novel model (RNN-GAN) that could generate time-varying fully developed flow for a long time. The spatiotemporal correlations of the generated flow are in good agreement with those of the DNS. This proves the usefulness of unsupervised learning in the generation of synthetic turbulence fields.