Bias Correction of Numerical Weather PredictionWind Fields in Southern Tamil Nadu RegionUsing Machine Learning Techniques

Accurate high resolution wind field prediction is essential for wind resource as-sessment, renewable energy planning, and regional weather analysis. AlthoughNumerical Weather Prediction (NWP) models such as the Weather Researchand Forecasting (WRF) model provide physically consistent wind forecasts, theiroutputs often suffer from systematic biases arising from uncertainties in surfacecharacteristics, simplified physical parameterizations, and resolution limitations.Furthermore, increasing model resolution to the kilometer scale significantlyraises computational cost. To address these challenges, this study presents amachine learning–based framework for bias correction of WRF-simulated windfields over the Southern Tamil Nadu region, with particular focus on the Mup-pandal wind farm area.An extensive validation of WRF configurations was first performed using mul-tiple physics scheme combinations and domain setups, evaluated against ERA5reanalysis data. The optimal configuration was identified and used to gener-ate three years (2023–2025) of wind simulations at 3 km × 3 km resolution.Significant biases were observed in the raw WRF outputs, motivating the appli-cation of an Artificial Neural Network (ANN) based bias correction approach.A Random Forest algorithm was employed for feature selection, followed byPrincipal Component Analysis (PCA) to reduce dimensionality while retaining95% of the variance. A feedforward neural network with multiple hidden layerswas trained to correct the U10 and V10 wind components, with the hyperbolictangent activation function yielding the best performance. The bias-correctedwind fields exhibited substantial improvement in mean and extremes, achieving low error metrics andstrong correlation with ERA5 data.The results demonstrate that combining physically based NWP simulations withmachine learning driven bias correction provides an accurate and computation-ally efficient approach for generating high-resolution wind fields. This hybridframework offers significant potential for wind energy assessment and localizedmeteorological applications in data-sparse regions.