Learn about the aims and vision of the WeatherGenerator in this short animated video
The objective of the WeatherGenerator is to improve weather and climate predictions, enhance renewable energy planning, and provide better tools for mitigating the effect of extreme events like floods and heatwaves. It will combine the latest machine learning with high performance computing, creating a robust tool for scientific discovery and real-world applications.
This way, the WeatherGenerator will ensure Europe remains at the forefront of innovation in weather and climate. The resulting European foundation model will be accessible for many diverse applications in the area of Earth system science.
Last week, the WeatherGenerator project brought people together for two inspiring online workshops dedicated to diversity, inclusion, and building more supportive research communities.
Everyone talks about the weather, but how is AI transforming the way we analyze weather data, evaluate forecasts, and push the boundaries of what is scientifically possible?
Everyone talks about the weather, but how is AI transforming the way we analyze weather data, evaluate forecasts, and push the boundaries of what is scientifically possible?
Are you planning to submit a paper that uses the Weather Generator Tool?
Join us for inspiring talks, engaging discussions, and meaningful networking on gender and diversity in research
The WeatherGenerator Service Call 2026 invites European research groups and industry partners outside the WeatherGenerator consortium to propose applications or integrations of the WeatherGenerator. Selected projects will receive up to 3 person-months of expert engineering support and will run through 2027. Deadline: 16 October 2026, 14:00 CET.
Join Martin Schultz and expert guests Peter Dueben and Christian Lessig from ECMWF for the first podcast episode on the role of AI in Weather Forecasting and how the WeatherGenerator plays a role in this.
Christian Lessig,
Martin Schultz,
Peter Dueben
Join Martin Schultz and expert guest Stefanie Hollborn from the German Weather Service (DWD) for the second podcast episode on AI weather modelling and seamless prediction.
Martin Schultz,
Peter Dueben,
Stefanie Hollborn
The WeatherGenerator FastEvaluation package is a flexible, open-source framework designed to bridge the gap between traditional weather forecast verification tools and the rapid iteration demands of modern machine learning–based weather modelling.
Ilaria Luise,
Savvas Melidonis,
Sorcha Owens,
Julius Polz
Running EU-wide Deep Learning projects for Weather The WeatherGenerator project is an ambitious Europe-wide project to build a “Large Language Model for the weather.” From the outset, this leads to a very practical challenge: how to coordinate the development of a state-of-the-art model across 6 High Performance Computing (HPC) systems and 10 research groups? Each HPC system is custom built with the purpose of maximizing processing power at the expense of ease of use or convenience. This experience is very different compared to using a public cloud such as Amazon Web Services, Azure, Google Cloud. Public clouds are meant to be cost effective to build and operate. They are the Ford T’s of large computing: easy to use, simple, adapted to many scenarios. Public cloud operators put a large focus on standardization and automation as well as ease of use for the final customers.
Timothee Hunter,
Christian Lessig
Machine learning powers WeatherGenerator, a global Earth system model for forecasting weather and climate impacts.
Christian Lessig
