Speakers
Description
Weather forecasts as provided by numerical weather prediction (NWP) models such as Harmonie-Arome, which is used by KNMI, are often (too) deterministic. Because of uncertainty in the forecast, it is preferable to have a full probability distribution instead.
Current statistical post-processing methods for providing a probabilistic forecast are not capable of using full spatial patterns from the NWP model. Recent developments in deep learning (notably convolutional neural networks) have made it possible to use large gridded input data sets. This could potentially be useful in statistical post-processing, since it allows us to use more spatial information. In this study we consider wind speed forecasts for 48 hours ahead, as provided by the Harmonie-Arome model. Convolutional neural networks, fully connected neural networks and Quantile Regression Forests are used to obtain probabilistic wind speed forecasts. Comparing these methods shows that Convolutional neural networks improve on the other methods, especially for medium to higher wind speeds.