Classifying regions of high model error within a data-driven RANS closure: Application to wind turbine wakes

Data-driven Reynolds-Averaged Navier-Stokes (RANS) turbulence closures are increasing seen as a viable alternative to general-purpose RANS closures, when LES reference data is available -- also in wind-energy. Parsimonious closures with few, simple terms have advantages in terms of stability, interpret-ability, and execution speed. However experience suggests that closure model corrections need be made only in limited regions -- e.g.\ in the near-wake of wind turbines and not in the majority of the flow. A parsimonious model therefore must find a middle ground between precise corrections in the wake, and zero corrections elsewhere. We attempt to resolve this impasse by introducing a classifier to identify regions needing correction, and only fit and apply our model correction there. We observe that such a classifier (which must be computed only from RANS-available quantities) is straightforward to construct, and accurate in operation. We further observe that the correction models are significantly simpler (with fewer terms) when limited to the identified regions than otherwise, but have similar or better accuracy. We apply our framework to three flows consisting of multiple wind-turbines in neutral conditions with interacting wakes.