High Performance Computing and Data science interfaces to predict, control and understand Fluid Mechanics

Petros Koumoutsakos
ETH Zurich

We live in exciting times characterised by a unique convergence of Computing and Data Sciences. Novel frameworks fuse data with mature numerical methods, innovative learning algorithms and software are effectively deployed on computers with unprecedented capabilities. Can we harness these new capabilities to solve some of the long standing problems in Fluid Mechanics such as turbulence modeling, flow control and information transfer across scales?

I will discuss our efforts to answer this question, celebrate successes as well as outline failures and open problems. I will demonstrate how Bayesian inference can assist model selection in molecular simulations, how long-shirt memory networks (may fail to) predict chaotic systems and how deep reinforcement learning (together with physical insight) can produce powerful flow control methodologies. I will argue that while Data and Computing offer wonderful capabilities it is human thinking that remains the critical aspect in our effort to understand Fluid Mechanics.


Back to Workshop III: HPC for Computationally and Data-Intensive Problems