WMO is a specialized agency of the United Nations (UN) with 193 Member States and Territories. It is the UN system’s authoritative voice on the state and behaviour of the Earth’s atmosphere, its interaction with the land and oceans, the weather and climate it produces and the resulting distribution of water resources.
Description of Activities on AI
Project 1: Research Board Concept Notes on Exascale Computing, Data Handling, and AI
The two Concept Notes identify challenges and opportunities on Exascale computing, data handling and AI for weather, climate, water and the environment and make recommendations to the WMO Research Board. It will serve as a guideline for the Research Board to plan its follow up activities and facilitate collaboration and interactions within WMO and with partners.
Project 2: Prize Challenge to improve Sub-seasonal to Seasonal Predictions using Artificial Intelligence
WMO launched the Challenge in June 2021 with the aim to improve, through AI/Machine Learning techniques, the current precipitation and temperature forecasts for 3 to 6 weeks into the future from the best computational fluid dynamic models available today.
This Challenge was organized by the Subseasonal-to-Seasonal Prediction Project (S2S Project), coordinated by the World Weather Research Programme (WWRP)/World Climate Research Programme (WCRP), in collaboration with the Swiss Data Science Center and the European Centre for Medium-Range Weather Forecasts (ECMWF).
After the submission phase closed until 31 October 2021, the Organizing Committee received 9 submissions from a wide range of countries, among which 5 submissions beat the calibrated ECMWF benchmark and climatology. Based on the ranked probability skill scores (RPSS) and the verification by an experts review for the top ranked submissions, the Organizing Committee selected the top 3 submissions.