Convolutional autoencoders for spatially-informed ensemble post-processing
This work addresses the loss of spatial predictability information in weather forecasting post-processing for meteorologists and climate scientists, representing an incremental improvement over existing neural network methods.
The paper tackled the problem of systematic errors in ensemble weather predictions by proposing convolutional autoencoders to learn compact spatial representations, augmenting location-specific post-processing models, and demonstrated benefits in a case study of 2-m temperature forecasts in Germany with concrete improvements in predictive accuracy.
Ensemble weather predictions typically show systematic errors that have to be corrected via post-processing. Even state-of-the-art post-processing methods based on neural networks often solely rely on location-specific predictors that require an interpolation of the physical weather model's spatial forecast fields to the target locations. However, potentially useful predictability information contained in large-scale spatial structures within the input fields is potentially lost in this interpolation step. Therefore, we propose the use of convolutional autoencoders to learn compact representations of spatial input fields which can then be used to augment location-specific information as additional inputs to post-processing models. The benefits of including this spatial information is demonstrated in a case study of 2-m temperature forecasts at surface stations in Germany.