Overview
All forecasts submitted to the AI Weather Quest are made openly available via the AI Weather Quest Data Portal. Participants are challenged to submit quintile-based probabilistic forecasts for near-surface air temperature, mean sea level pressure, and accumulated precipitation, targeting lead times of days 19 to 25 (week 3) and 26 to 32 (week 4). This guide is designed to support forecast download and use of individual files.
Data publication timetable
The first year of the AI Weather Quest is divided into four 13-week competitive periods. After each period, and following the end-of-period webinar and forecast evaluation, all submitted forecasts from that phase will be made openly available according to the timetable below (where each acronym refers to the forecasted months, i.e. SON is September, October, November):
- SON 2025: 12th December 2025
- DJF 2025/2026: 16th March 2026
- MAM 2026: 15th June 2026
- JJA 2026: 14th September 2026
Portal directory structure
To facilitate access, forecasts are organised into directories that can be browsed by either:
- Forecast initialisation date (by_fc_date)
- Participating team (by_team)
The following directory structures is followed:
- by_fc_date >> by_team >> by_model >> forecasts
- 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)
Filename formatting
A separate NetCDF file is provided for each forecasted variable submitted by a team. Files are named using the following naming convention:
[variable]_[fc_init_date]_p[fc_window]_[teamname]_[modelname].nc where:
- variable: The forecasted variable. Options are:
- 'tas': Near-surface temperature (weekly-mean)
- 'mslp': Mean sea level pressure (weekly_mean)
- 'pr': Precipitation (weekly-accumulated)
- fc_start_date: The forecast initialisation date in format YYYYMMDD (e.g., ‘20250515’ for 15th May 2025).
- fc_window: The selected forecasting window. Valid options are:
- '1': Weekly-mean forecasts for days 19 to 25 inclusive.
- '2': Weekly-mean forecasts for days 26 to 32 inclusive.
- teamname : The associated team name with the submitted forecast.
- modelname: The associated model name with the submitted forecast.
The following teams webpage contains Information regarding individual teams and their associated models.
Forecast download
Downloading either a set (zip files) or individual forecast through a web browser is simple. Just click on a chosen file and it will automatically download.
Forecast file content
Licence information
This dataset is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) licence. Full licence terms can viewed here.
Contact / support information
For support with accessing AI WQ sub-seasonal forecast data, please use one of the following communication channels:
Dataset citation / DOI
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.