The Wind Farm Layout Optimization problem involves finding the optimal positions for wind turbines on a wind farm site. Current Metahueristic based methods make use of a combination of turbine specifications and parameters, mathematical models and empirically produced power production equations to estimate the energy output of a real wind farm [15]. The overarching variable in any optimisation function is wind speed - this is what used to determine the power generated. Therefore, accurate predictions of wind speeds at specific points across the volume of the site are needed. In this paper, Computational Fluid Dynamics (CFD) was used to simulate a full scale rotating wind turbine blade with fluid (air) at various wind speeds flowing past the turbine. The wake effect can be observed and leads to decrease in wind speeds, as expected. Wind speed at specific x,y and z (3D) coordinates were sampled and used as input to common Machine Learning regression algorithms to create different surrogate models. This was needed as each individual CFD experiment takes approximately 8 hours to complete, so it is not feasible to continuously repeat these simulations inside a metaheuristic optimiser.