Dataset for denoising diffusion probabilistic model to generate 10-m wind speed ensemble nowcast

This dataset is used to train and test a diffusion model designed to generate ensemble nowcasts of 10-meter wind speed. The dataset is stored in .npy format and contains deterministic nowcasts of wind speed at different forecast lead times, along with their corresponding forecast errors. As a result, the true wind speed can be derived by subtracting the error from the forecast. The data has a spatial resolution of 1 km and a temporal resolution of 1 hour. The last two numbers in each .npy filename represent the grid indices in the y and x directions, corresponding to the cropped subregion from the original domain.