Self-Attentive Transformer for Fast and Accurate Postprocessing of Temperature and Wind Speed Forecasts

作者：Aaron Van Poecke, Tobias Sebastian Finn, Ruoke Meng, Joris Van den Bergh, Geert Smet, Jonathan Demaeyer, Piet Termonia, Hossein Tabari, Peter Hellinckx · 发表于：Artificial Intelligence for the Earth Systems · 年份：2025 · DOI：10.1175/aies-d-24-0127.1 · 被引用次数：1 · 研究领域：Energy Load and Power Forecasting

Abstract Current postprocessing techniques often require separate models for each lead time and disregard possible interensemble relationships by either correcting each member separately or by employing distributional approaches. In this work, we tackle these shortcomings with an innovative, fast, and accurate transformer which postprocesses each ensemble member individually while allowing information exchange across variables, spatial dimensions, and lead times by means of multiheaded self-attention. Weather forecasts are postprocessed over 20 lead times simultaneously while including up to fifteen meteorological predictors. We use the EUPPBenchmark dataset for training which contains ensemble predictions from the European Centre for Medium-Range Weather Forecasts’ integrated forecasting system alongside corresponding observations. The work presented here is the first to postprocess the 10- and 100-m wind speed forecasts within this benchmark dataset, while also correcting 2-m temperature. Our approach significantly improves the original forecasts, as measured by the continuous ranked probability score (CRPS), with 16.5% for 2-m temperature, 10% for 10-m wind speed, and 9% for 100-m wind speed, outperforming a classical member-by-member approach employed as a competitive benchmark. Furthermore, being up to 6 times faster, it fulfills the demand for rapid operational weather forecasts in various downstream applications, including renewable energy forecasting. Significance Sta...