In this numerical study, we use a multi-scale version of physics-informed neural network (PINN) for wind field reconstruction from LiDAR measurements. The reference velocity field is obtained from high-fidelity large-eddy simulation of neutral atmospheric boundary layer, and the LiDAR measurement strategy is restricted to that of a real LiDAR. The multi-scale PINN reconstructs the velocity field by minimizing a combination of the L2-error with respect to the LiDAR measurements and residuals of the governing equations. Our most significant finding is that adding a multi-scale layer to PINN enables us to: (i) capture wider range of scales, (ii) reconstruct the flow field outside the LiDAR scanning area, and (iii) reach faster convergence. We also find that for volumetric flow reconstruction and to deal with uncertainty in the wind direction, the reconstruction accuracy can be greatly improved by employing multiple LiDAR devices. Overall, our results show that the normalized errors in the reconstructed wind field are lower than 5% for all the experiments conducted in this study and that the errors do not increase even in the presence of measurement noise levels of typical LiDAR. These findings show the feasibility of three-dimensional dynamic wind field reconstruction across large wind farms using LiDAR devices.

Wind energy is crucial to the transition to a carbon-free world. However, new wind farms are increasingly sited on complex terrain, whose influence on turbine performance is still not well understood. Here large-eddy simulations are performed on the flow around a wind turbine sited on three different terrain types: a flat ground, a 2-D hill, and a 3-D hill. We find that hilly terrain can increase the power generated via the speed-up effect, but that it can also increase the wake deficit and deflect the wake center, potentially affecting any turbines downstream. We interpret this deflection as being caused by the topography-induced vertical velocity component, which we model with a passive tracer method. By combining this passive tracer method with engineering-focused wake models, we obtain improved predictions of the velocity deficit and wake deflection. Such a hybrid strategy is fast and accurate, facilitating the design of wind farms sited on steep hilly terrain, which often experience flow separation at the backslope.