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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Van Poecke, Aaron, Finn, Tobias Sebastian, Meng, Ruoke, Bergh, Joris Van den, Smet, Geert, Demaeyer, Jonathan, Termonia, Piet, Tabari, Hossein, Hellinckx, Peter
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909687561060352
author Van Poecke, Aaron
Finn, Tobias Sebastian
Meng, Ruoke
Bergh, Joris Van den
Smet, Geert
Demaeyer, Jonathan
Termonia, Piet
Tabari, Hossein
Hellinckx, Peter
author_facet Van Poecke, Aaron
Finn, Tobias Sebastian
Meng, Ruoke
Bergh, Joris Van den
Smet, Geert
Demaeyer, Jonathan
Termonia, Piet
Tabari, Hossein
Hellinckx, Peter
contents Current postprocessing techniques often require separate models for each lead time and disregard possible inter-ensemble 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 multi-headed self-attention. Weather forecasts are postprocessed over 20 lead times simultaneously while including up to fifteen meteorological predictors. We use the EUPPBench dataset for training which contains ensemble predictions from the European Center for Medium-range Weather Forecasts' integrated forecasting system alongside corresponding observations. The work presented here is the first to postprocess the ten and one hundred-meter wind speed forecasts within this benchmark dataset, while also correcting two-meter temperature. Our approach significantly improves the original forecasts, as measured by the CRPS, with 16.5\% for two-meter temperature, 10\% for ten-meter wind speed and 9\% for one hundred-meter wind speed, outperforming a classical member-by-member approach employed as a competitive benchmark. Furthermore, being up to six times faster, it fulfills the demand for rapid operational weather forecasts in various downstream applications, including renewable energy forecasting.
format Preprint
id arxiv_https___arxiv_org_abs_2412_13957
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-attentive Transformer for Fast and Accurate Postprocessing of Temperature and Wind Speed Forecasts
Van Poecke, Aaron
Finn, Tobias Sebastian
Meng, Ruoke
Bergh, Joris Van den
Smet, Geert
Demaeyer, Jonathan
Termonia, Piet
Tabari, Hossein
Hellinckx, Peter
Machine Learning
Atmospheric and Oceanic Physics
Current postprocessing techniques often require separate models for each lead time and disregard possible inter-ensemble 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 multi-headed self-attention. Weather forecasts are postprocessed over 20 lead times simultaneously while including up to fifteen meteorological predictors. We use the EUPPBench dataset for training which contains ensemble predictions from the European Center for Medium-range Weather Forecasts' integrated forecasting system alongside corresponding observations. The work presented here is the first to postprocess the ten and one hundred-meter wind speed forecasts within this benchmark dataset, while also correcting two-meter temperature. Our approach significantly improves the original forecasts, as measured by the CRPS, with 16.5\% for two-meter temperature, 10\% for ten-meter wind speed and 9\% for one hundred-meter wind speed, outperforming a classical member-by-member approach employed as a competitive benchmark. Furthermore, being up to six times faster, it fulfills the demand for rapid operational weather forecasts in various downstream applications, including renewable energy forecasting.
title Self-attentive Transformer for Fast and Accurate Postprocessing of Temperature and Wind Speed Forecasts
topic Machine Learning
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2412.13957