WeatherGenerator Project kicks off: Transforming climate prediction with AI

The WeatherGenerator project, funded by the EU’s Horizon Europe program, officially launched last week with a virtual kickoff meeting. This groundbreaking initiative aims to revolutionise weather and climate predictions by leveraging advanced AI and machine learning to develop a cutting-edge European foundation model for Earth system science.

Coordinated by the European Centre for Medium-Range Weather Forecasts (ECMWF), WeatherGenerator unites 16 top-tier European institutions, including universities, meteorological institutes, and energy organisations. The project will enhance forecasting capabilities, optimize renewable energy planning, and improve disaster preparedness for extreme weather events such as floods and heatwaves.

Peter Dueben, Head of Earth System Modelling at ECMWF, highlighted the project’s potential:

“The WeatherGenerator will provide more accurate, cost-effective simulations of Earth system dynamics, contributing to a deeper understanding of how weather and climate events unfold and better representation and prediction of extreme events across various timescales. These advancements will enable more efficient planning and resource allocation, particularly in areas crucial to Europe’s climate resilience.”

Key objectives include:

• Developing a state-of-the-art AI model for simulating Earth system dynamics.

• Improving weather and climate predictions across multiple timescales.

• Supporting disaster response with enhanced forecasting tools.

• Providing open-source tools and data to foster collaboration in climate research.

• Training AI specialists in Earth sciences to ensure long-term project impact.

Project Partners:

• EUROPEAN CENTRE FOR MEDIUM-RANGE WEATHER FORECASTS (ECMWF) – INT

• Forschungszentrum Juelich (FZJ) – Germany

• Norwegian Meteorological Institute (MetNor) – Norway

• Max-Planck-Gesellschaft zur Förderung der Wissenschaften e.V. (MPG) – Germany

• Royal Netherlands Meteorological Institute (KNMI) – Netherlands

• Météo-France (MetFrance) – France

• Swedish Meteorological and Hydrological Institute (SMHI) – Sweden

• UK MetOffice (UKMO) – UK

• Centro Euro-Mediterraneo sui Cambiamenti Climatici (CMCC) – Italy

• Netherlands eScience Center (eScience) – Netherlands

• Buluttan (Buluttan) – Turkey

• Kajo Services (KAJO) – Slovakia

• Latest Thinking (LT) – Germany

• Statkraft (Statkraft) – Norway

• Eidgenössische Technische Hochschule (ETHZ) – Switzerland

• MeteoSwiss (MetSwiss) – Switzerland

By combining expertise in AI, climate science, and energy, WeatherGenerator is set to drive Europe’s leadership in AI-powered climate solutions.

For more details, visit WeatherGenerator.eu

The WeatherGenerator project (grant agreement No101187947) is funded by the European Union. Views and opinions expressed are those of the author(s) only and do not necessarily reflect those of the EU or the Commission. Neither the EU nor the granting authority can be held responsible for them.