...
The AI Weather Quest is a collaborative forecasting challenge hosted by ECMWF, designed to explore the potential of AI and machine learning in medium-range weather prediction. Participating teams are challenged with providing quintile-based probabilistic forecasts for three key variables: near-surface air temperature (tas), mean sea level pressure (mslp), and accumulated precipitation (pr). Forecasts target lead times of days 19 to 25 (week 3) and days 26 to 32 (week 4).
This guide explains how to use the leaderboards page effectively and track the evolution of team and model performance over time.
Leaderboards page content
...
Starting 19 September 2025, the
...
Leaderboards page will display:
- Ranked Probability Skill Scores (RPSS) for submitted forecasts
- Tables showing team and model rankings
- Evolution graphs tracking performance over time
Evaluation results are indeed only made available after the evaluation date (day 37 of each competition week) has passed.
This guide explains how to use the leaderboards page effectively and track the evolution of team and model performance over time.
Using the filters
Filters apply to all elements on the page, including RPSS tables and evolution graphs. By default, the page displays the latest evaluated period and week, the first forecast window (Days 19–25), and variable-averaged scores.
To customize your view, use the following options:
...
All rankings are based on the RPSS of each team's best-performing model. However, individual model ranks and scores are also visualised, allowing users to compare performance across multiple submissions from the same team.
Click any RPSS score in the table to view the corresponding forecast in the ECMWF-hosted sub-seasonal AI forecasting portal.
There are two main types of RPSS tables:
...