Abstracted/indexed

We develop two machine-learning-based approaches to temporally extrapolate uncertainty in hub-height wind speed modeled by a numerical weather prediction model. We test our approaches in the California Outer Continental Shelf, where a significant offshore wind energy development is currently being planned, and we find that both provide accurate results.

This article presents a novel method to improve offshore surface wind speeds estimated by Synthetic Aperture Radar satellites and extrapolate them to higher altitudes. It can provide maps of the offshore extractible wind power up to 200 m and thus complement numerical models, especially in coastal areas. The method uses geometrical parameters of the sensor and parameters related to the atmospheric stability, combining them with machine learning. The final accuracy at 200 m is within 4 %.

Wind turbine wake behavior in hilly terrain depends on various atmospheric conditions. We modeled a wind turbine located on top of a ridge in Portugal during typical nighttime and daytime atmospheric conditions and validated these model results with observational data. During nighttime conditions, the wake deflected downwards following the terrain. During daytime conditions, the wake deflected upwards. These results can provide insight into wind turbine siting and operation in hilly regions.

A model for computing vertical-axis wind turbine farms was developed using computational fluid dynamics open-source software. This model has the potential of evaluating wind farm configurations which can lead to a higher annual energy yield. Such configurations have not been studied thoroughly due to the fact that most analysis tools are computational expensive, this model can be run in personal computers within a matter of minutes or hours depending on the number of turbines.