Three-dimensional generative adversarial networks for turbulent flow estimation from wall measurements

TL;DR

This paper introduces a novel 3-D GAN approach for reconstructing entire turbulent flow fields from wall measurements, improving accuracy and efficiency over previous methods and enabling better interpretation of flow structures.

Contribution

First application of a single 3-D GAN for full turbulent flow reconstruction from wall data, reducing computational cost and enhancing structural interpretability.

Findings

3-D GAN accurately reconstructs flow with comparable error to plane-based methods.

Wall-attached structures are predicted more accurately than detached ones.

Reconstruction accuracy varies with structure size and type, favoring smaller sweeps and larger ejections.

Abstract

Different types of neural networks have been used to solve the flow sensing problem in turbulent flows, namely to estimate velocity in wall-parallel planes from wall measurements. Generative adversarial networks (GANs) are among the most promising methodologies, due to their more accurate estimations and better perceptual quality. This work tackles this flow sensing problem in the vicinity of the wall, addressing for the first time the reconstruction of the entire three-dimensional (3-D) field with a single network, i.e. a 3-D GAN. With this methodology, a single training and prediction process overcomes the limitation presented by the former approaches based on the independent estimation of wall-parallel planes. The network is capable of estimating the 3-D flow field with a level of error at each wall-normal distance comparable to that reported from wall-parallel plane estimations and at a lower training cost in terms of computational resources. The direct full 3-D reconstruction also unveils a direct interpretation in terms of coherent structures. It is shown that the accuracy of the network depends directly on the wall footprint of each individual turbulent structure. It is observed that wall-attached structures are predicted more accurately than wall-detached ones, especially at larger distances from the wall. Among wall-attached structures, smaller sweeps are reconstructed better than small ejections, while large ejections are reconstructed better than large sweeps as a consequence of their more intense footprint.