Check out our recent open-access publication in Physics of Fluids on "Spatial prediction of the turbulent unsteady von Kármán vortex street using Echo State Networks". We showed that the stable quality of the reconstructed fields over a long period, along with the simplicity of the machine learning algorithm (ESN), which relied on coarse experimental data only, demonstrates the viability of spatial prediction as a suitable method for machine learning application in turbulence.

 

Reference:  M. Sharifi Ghazijahani, F. Heyder, J. Schumacher, C. Cierpka; Spatial prediction of the turbulent unsteady von Kármán vortex street using echo state networks. Physics of Fluids 2023; 35 (11): 115141. https://doi.org/10.1063/5.0172722

TU Ilmenau/Mohammad Sharifi