Check out our recent open-access publication in Engineering Applications of Artificial Intelligence: "On the spatial prediction of the turbulent flow behind an array of cylinders via echo state networks." In this study, we demonstrate how Echo State Networks (ESNs) can effectively predict the turbulent flow field behind an array of seven cylinders in the spatial domain. By training the ESN on low-resolution experimental data, the network successfully predicted realistic flow structures, preserving the synchronization and arrangement of vortex streets. We explored four prediction scenarios-forward, backward, vertical, and central-with the central vortex street proving to be the most efficient region for spatial predictions. These findings highlight the potential of ESNs for spatial modeling of complex turbulent flows with minimal sensitivity to hyperparameters. Reference: Mohammad Sharifi Ghazijahani, Christian Cierpka; On the spatial prediction of the turbulent flow behind an array of cylinders via echo state networks. Engineering Applications of Artificial Intelligence 2025; 144, 110079:https://doi.org/10.1016/j.engappai.2025.110079