Forecasting of the wind speed and power generation for a wind farm has always been quite challenging and has importance in terms of balancing the electricity grid and preventing energy imbalance penalties. This study focuses on creating a hybrid model that uses both numerical weather prediction model and gradient boosting machines (GBM) for wind power generation forecast. Weather Research and Forecasting (WRF) model with a low spatial resolution is used to increase temporal resolutions of the computed new or existing variables whereas GBM is used for downscaling purposes. The results of the hybrid model have been compared with the outputs of a stand-alone WRF which is well configured in terms of physical schemes and has a high spatial resolution for Yahyalı wind farm over a complex terrain located in Turkey. Consequently, the superiority of the hybrid model in terms of both performance indicators and computational expense in detail is shown.

A country-based day-ahead wind power generation forecast (WPGF) model with a grid selection algorithm and feature selection models was proposed in this study. Atmospheric variables extracted from 300, 500, 700 hPa pressure levels, and surface level of ERA5 reanalysis data with 2.5° spatial resolution were used to train/validate the categorical boosting (CatBoost) model. A special grid selection algorithm was proposed by considering Turkey’s spatial distribution of wind power plants. The day-ahead forecasts of ECMWF’s HRES (High-resolution) were used as the test subset, therefore, paving the way for the operational use of the model. The proposed model could be considered much as a specialized machine learning based downscaling method for country-based WPGF due to using numerical weather prediction model outputs as its input. Results showed that the proposed model that uses fewer features has outperformed the other models with a normalized root mean square error of 7.6% and coefficient of determination of 0.8989.

Short-term wind speed forecast model that uses both supervisory control and data acquisition (SCADA) based data and weather research and forecasting (WRF) model outputs for Urla wind power plant (WPP) has been proposed in this study. Two different WRF models were run to gather atmospheric variables from four surrounding grids of Urla WPP and calculate weather patterns affecting Urla WPP. After detecting outliers in the SCADA data by coupling of k-mean and isolation forest (IF) methods, statistical methods were used for data treatment and the outputs of WRF models were used for missing data imputation. The effect of each data type and data preprocessing techniques on the model was evaluated separately. The best model performance was achieved with 0.9085 [ ], and 0.81 MAE in the dataset which includes each data type and each data preprocessing was applied on. Otherwise, the dominant weather pattern affecting Urla WPP was found to be purely advective and the best result was achieved in this pattern.

This study presents an integrated framework for offshore wind resource assessment and wind farm micrositing in the Northern Aegean Sea of Türkiye by combining machine learning-assisted measure–correlate–predict (MCP) modelling, long-term reanalysis data and computational fluid dynamics (CFD). One year of measurements from a 41 m meteorological mast on Küçük Ada, offshore Aliağa, İzmir, was analyzed together with a 21-year ECMWF Reanalysis v5 (ERA5) dataset. The measurements indicated a mean annual wind speed of 8.07 m/s, a wind shear exponent of 0.049, a Weibull shape parameter of 2.06 and a persistent northeasterly wind regime. Long-term conditions were reconstructed using 64 meteorological and cyclic predictors derived from four ERA5 grid points and their bilinear interpolation to the mast location. Five H₂O algorithm families were evaluated using randomized grid searches and 12-fold temporal cross-validation. Distributed Random Forest provided the best performance for 100 m wind speed, with RMSE = 1.969 m/s, MAE = 1.504 m/s, bias = −0.027 m/s and an out-of-fold Pearson correlation coefficient of r = 0.884. TreeSHAP analysis was applied to interpret predictor contributions. High-resolution WindSim simulations with 28.75 million cells, ALOS PALSAR topography and CORINE land-cover data supported turbine micrositing. The proposed 1.43 GW wind farm yielded 5494.5 GWh/year after wake losses, with a capacity factor of 43.9% and an overall wake loss of 5.2%. The framework provides a robust basis for offshore wind development in Türkiye.