Post-processing methods improve temperature and wind forecasts at new locations
Statistical versus machine learning-based spatial interpolation of post-processed ensemble weather forecasts
Machine Learning
Summary
Weather forecasts often use groups of predictions that need adjusting to be more accurate. The authors compared traditional statistical methods to newer machine learning techniques to improve forecasts of temperature and wind speed in Germany, especially at places without weather stations. They found that while no single approach worked best for every situation, adjusting forecasts this way generally made them better than raw predictions. The authors also introduced a new way to combine forecasts that takes altitude into account, which slightly improved temperature predictions at unobserved locations.
What this means in practice
- •For weather forecasting teams: Generate more accurate temperature and wind speed forecasts at locations without direct observations using improved post-processing methods.
- •For renewable energy operators: Enhance wind speed predictions at unmonitored sites to optimize wind farm operations and grid integration.
Authors
Mária Lakatos
Abstract
Statistical post-processing improves ensemble weather forecasts, but generating calibrated predictions at locations without observations remains challenging. This study compares statistical and machine-learning-based methods for post-processing ECMWF 2-m temperature and 10-m wind speed forecasts at observed and unobserved stations in Germany. We consider EMOS-based approaches, distributional regression networks, Transformers, and graph neural networks under both limited and extended predictor settings. For temperature, we also investigate linear forecast combinations and propose an altitude-aware linear pool (ALP). The results show that post-processing improves upon the raw ensemble in most settings, but no single method performs best across all variables, station groups, and evaluation metrics. The proposed ALP provides a small but significant improvement over the standard linear pool at unobserved locations.