From coarse wall measurements to turbulent velocity fields with deep learning.

This work evaluates the applicability of super-resolution generative adversarial networks (SRGANs) as an intermediate step for the reconstruction of wall-parallel velocity fields from coarse wall measurements. The analysis has been carried out with a database of a turbulent open-channel flow with friction Reynolds number $Re_{\tau}=180$ generated through direct numerical simulation. Coarse wall measurements have been generated with three different downsampling factors $f_d=[4,8,16]$ from the high-resolution fields, and wall-parallel velocity fields have been reconstructed at four inner-scaled wall-normal distances $y^+=[15,30,50,100]$. Even though lower resolutions make it more challenging to achieve high accuracy predictions, the suggested SRGAN-based network helps us to achieve acceptable results. The proposed novel DNN-based methodology to reconstruct flow fields from coarse wall measurements in turbulent flows has great potential for opposition-control applications relying on non-intrusive sensing.