MétaCan
Menu
Back to cohort
Record W4405626796 · doi:10.1175/aies-d-24-0127.1

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

2025· preprint· en· W4405626796 on OpenAlexaff
Aaron Van Poecke, Tobias Sebastian Finn, Ruoke Meng, Joris Van den Bergh, Geert Smet, Jonathan Demaeyer, Piet Termonia, Hossein Tabari, Peter Hellinckx

Bibliographic record

VenueArtificial Intelligence for the Earth Systems · 2025
Typepreprint
Languageen
FieldEngineering
TopicEnergy Load and Power Forecasting
Canadian institutionsUnited Nations University Institute for Water, Environment, and Health
Fundersnot available
KeywordsTransformerWind speedComputer scienceSpeedupEnvironmental scienceMeteorologyElectrical engineeringEngineeringPhysicsParallel computingVoltage

Abstract

fetched live from OpenAlex

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 Statement Accurate weather forecasts are essential for the daily functioning of a myriad of societal and economical actors. Current weather forecasting models, however, still contain significant biases and insufficient model uncertainty. Therefore, in this study, we develop a model to improve the accuracy of wind speed and temperature forecasts, two essential weather variables, for e.g., the agricultural, transport, or renewable energy sector. The method is a fast and flexible deep learning algorithm which improves around 16.5% for temperature and 10% for wind speed as compared to the original forecasts. Future research could further enhance accuracy by tailoring the model to specific geographic regions classified based on different climatological conditions.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.007
Threshold uncertainty score0.018

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0050.003

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.034
GPT teacher head0.270
Teacher spread0.236 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueArtificial Intelligence for the Earth SystemsSame topicEnergy Load and Power ForecastingFrench-language works237,207