When using the provided data, please cite the following article: Amato, F., Guignard, F., Walch, A., Mohajeri, N., Scartezzini, J. L., & Kanevski, M. (2021). Spatio-temporal estimation of wind speed and wind power using machine learning: predictions, uncertainty and technical potential. arXiv preprint arXiv:2108.00859. Summary: This dataset contains an estimation of the average yearly wind speed and of the wind power potential for Switzerland, at a spatial resolution of 250 x 250 meters and over the period from 2008 to 2017. Wind speed data are obtained by modelling data collected at an hourly frequency on a set of up to 208 monitoring stations over the country. The data are then interpolated using a spatio-temporal machine learning model, allowing the estimation of wind speed and its uncertainty at unsampled locations. Then, the modelled spatio-temporal wind speed field is used to estimate the wind power. This is computed based on the characteristic parameters of an Enercon E-101 wind turbine at 100 meters hub height. The latter indicates the distance from the turbine platform to the rotor of an installed wind turbine, showing how high the turbine stands above the ground without considering the length of the turbine blades. The hourly estimations of wind speed are then averaged over each of the ten years studied, for each 250 x 250 spatial location, while wind power data are summed over each year for each spatial unit. Advantages and limitations of the proposed method are discussed in Amato et al. (2021). Data description: The hourly estimation of wind speed and power for Switzerland from 2008 to 2017 are available under request. Here we share the annual values. For both wind speed and power, the data are available over 660697 spatial units of 250 x 250 meters each, covering the entire Swiss territory. Check details in the file Data_description.pdf. Data are provided in the pickle format, see https://docs.python.org/3/library/pickle.html#module-pickle.

{"references": ["Amato, F., Guignard, F., Walch, A., Mohajeri, N., Scartezzini, J. L., & Kanevski, M. (2021). Spatio-temporal estimation of wind speed and wind power using machine learning: predictions, uncertainty and technical potential. arXiv preprint arXiv:2108.00859."]}