High-resolution wind resource maps are essential for wind farm siting and renewable-energy planning, but national-scale assessment is often limited by sparse meteorological stations and the coarse resolution of reanalysis products. This study introduces a self-supervised Physics-Constrained Super-Resolution CNN (PC-SRCNN) that enhances ERA5 wind fields from 0.25° to 0.025°, for settings lacking a high-resolution, hourly-resolved reference wind field, by embedding kinematic and vertical-profile consistency as soft regularization penalties, without solving the full Navier-Stokes momentum balance. The framework was evaluated against 190 independent INMET stations, alongside interpolation, data-driven, and climatological baselines, using a station-wise bootstrap and the Diebold-Mariano test. The full model reduced the bootstrap MAE from 1.22 to 1.04 m/s relative to native ERA5, a 14.85% improvement confirmed by both tests, and achieved a vertical-profile of 0.90 against baselines below 0.70. Ablation shows physical regularization is not automatically beneficial: a variant constrained only by horizontal kinematics performed significantly worse than ERA5, with gains obtained only when vertical logarithmic-profile consistency was included. All other baselines evaluated were statistically indistinguishable from native ERA5 against station observations. These results indicate that sharper spatial detail alone is insufficient to improve wind-resource estimates unless supported by physically meaningful, vertically consistent constraints.
This work presents a framework for national-scale onshore wind farm screening in Brazil based on turbine technology. The approach integrates ERA5 hourly wind fields, turbine technical specifications, a Random Forest Regression (RFR)-based turbine power-output surrogate model, and GIS-based spatial exclusion analysis. The RFR model was trained using 821 empirical power curves, enabling different real turbine models to be evaluated within a unified framework. Seven representative turbines were evaluated across five wind farm configurations under capacity-factor thresholds of 0.20, 0.25, and 0.44. Results show that turbine technology substantially changes site suitability: for , viable locations ranged from 116 to 1846, and for , from 19 to 1175. Only 298 locations nationally reached , with the two best-performing configurations accounting for 297 of them. Even between these similarly rated turbines, neither dominated nationally: one outperformed the other at 58.5% of viable locations, with the reverse holding for the remaining 41.5%. Under the cost assumptions adopted, only the best-performing configurations achieved levelized costs of energy competitive with recently contracted wind energy prices in Brazil. Validation against the Icaraizinho wind farm yielded an MAPE of 6.40%. Overall, the results demonstrate that wind potential is technology-dependent and should be assessed using turbine-specific performance models.