Assimilation of statistical data into turbulent flows using physics-informed neural networks

When modeling turbulent flows, it is often the case that information on the forcing terms or the boundary conditions is either not available or overly complicated and expensive to implement. Instead, some flow features, such as the mean velocity profile or its statistical moments, may be accessible through experiments or observations. We present a method based on physics-informed neural networks to assimilate a given set of conditions into turbulent states. The physics-informed method helps the final state approximate a valid flow. We show examples of different statistical conditions that can be used to prepare states, motivated by experimental and atmospheric problems. Lastly, we show two ways of scaling the resolution of the prepared states. One is through the use of multiple and parallel neural networks. The other uses nudging, a synchronization-based data assimilation technique that leverages the power of specialized numerical solvers.