Overview
The AI Weather Quest (AI WQ), organised by ECMWF, is an ambitious international competition designed to harness artificial intelligence (AI) and machine learning (ML) in advancing weather forecasting. It challenges participants to produce and submit sub-seasonal weather forecasts – covering the critical weeks between medium-range and seasonal predictions – using AI/ML models.
This dataset includes all submitted forecasts during the competition phase of the Quest. Teams were challenged to submit global, quintile-based probabilistic forecasts of at least one of the following variables:
- Weekly-mean near-surface (2m) temperature (tas)
- Weekly-mean sea level pressure (mslp)
- Weekly-accumulated precipitation (pr)
Forecasts were requested at a 1.5-degree latitude/longitude resolution for one of the following lead times (inclusive):
- Days 19 to 25 (week 3)
- Days 26 to 32 (week 4)
Further details on submission guidelines are available on the AI Weather Quest website, and all submitted forecasts can be visualised through the Quest’s forecast portal.
Data publication timetable
The first year of the AI Weather Quest is divided into four 13-week competitive periods. Once the last set of forecasts within a competition period have been evaluated, all submitted predictions from that phase are made openly available. Publication dates for each period are:
- September, October, November (SON) 2025: 15th December 2025
- December, January, February 2025/2026: 16th March 2026
- March, April, May 2026: 15th June 2026
- June, July, August 2026: 14th September 2026
Directory structure
To facilitate access, forecasts are organised into directories that can be browsed by either:
- Forecast initialisation date (by_fc_date): by_fc_date >> by_team >> by_model >> forecasts
- Participating team (by_team): by_team >> by_model >> by_fc_date >> forecasts
A separate NetCDF file is provided for each forecasted variable and lead time submitted by a team.
For more efficient downloading, we also provide .zip archives containing all forecasts either:
- submitted by a given team (by_team_zipfiles), or
- issued for a given initialisation date (by_fc_date_zipfiles)
Further guidance on file content and recommended download methods is available on the following confluence page.
Contact / support information
For support with accessing AI WQ sub-seasonal forecast data, please use one of the following communication channels:
- Public forum.
- Email: aiweatherquest@ecmwf.int
Dataset citation & licence information
When using this dataset, please cite the dataset DOI (provided below) and the following reference:
Loegel, O., Talib, J., Vitart, F., Hoffmann, J. and Chantry, M., 2025. The AI Weather Quest: an international competition for sub-seasonal forecasting with AI. Machine Learning: Earth, 1(1), p.010701. https://doi.org/10.1088/3049-4753/adf649
This dataset is released under ECMWF's general licence and the Creative Commons Attribution 4.0 International (CC BY 4.0) licence.
Acknowledgement
If applicable, please acknowledge the AI Weather Quest competition as follows: “This dataset was produced as part of the AI Weather Quest competition organised by ECMWF (2025-2026)."