- Coordinator
- Alfred-Wegener-Institut Helmholtz-Zentrum Fur Polar- Und Meeresforschung, Germany
- Runs
- 1 September 2026 to 31 August 2030
- Status
- Running
- EU funding
- €10.0m
- Total cost
- —
- Partners
- 13 organisations in 6 countries
- Type
- Research and Innovation Action
- Grant agreement
- 101290971
What the project is doing
In the project's own words, from its summary on CORDIS.
CLAIMA will build a European AI-driven climate digital twin platform that delivers fast, high-resolution and trustworthy climate simulations for science, industry and policy. It will integrate three strands of climate AI (emulators of physicsbased models, deep-learning downscaling, and emerging foundation models) within a modular, standards-based system that follows FAIR data and open API principles. Rigorous evaluation, provenance tracking and uncertainty quantification will ensure scientific integrity at every stage.
The platform will orchestrate end-to-end workflows across EuroHPC systems and European AI Factories, while interoperating seamlessly with Destination Earth, and will be demonstrated in this operationally relevant environment to reach TRL 6. The project will also provide an indicative estimate of the costs of operating the platform in such a production-like environment, including compute and service operation costs. The project has three main objectives.
First, CLAIMA will adapt and validate state-of-the-art AI climate models against observations and high-fidelity simulations, creating engines that are both fast and reliable. Second, it will engineer a modular and interoperable digital twin platform to support training, inference, evaluation and user access across Europe’s research infrastructures. Third, it will demonstrate value in real-world applications, including climate science, through use cases co-designed with stakeholders.
The system will combine a robust web-based interface with a natural-language assistant, with clear communication of AI use, limits and impacts. CLAIMA directly addresses HORIZON-INFRA-2025-01-TECH-04 by applying GenAI4EU-aligned methods to set up and manage complex modelling across research infrastructures. It will establish best practices for AI model generation and data fusion, demonstrate interoperability with DestinE, and enable innovative applications in key impact sectors.
By providing a durable European infrastructure for climate AI, CLAIMA will accelerate scientific discovery, support climate adaptation, and strengthen Europe’s global leadership in trustworthy digital twins.
Topics
Who is involved
| Organisation | City | Country | Role |
|---|---|---|---|
| Alfred-Wegener-Institut Helmholtz-Zentrum Fur Polar- Und Meeresforschung | Bremerhaven | Germany | Coordinator |
| Deutsches Klimarechenzentrum GmbH | Hamburg | Germany | Participant |
| Max-Planck-Gesellschaft Zur Forderung Der Wissenschaften eV | Munchen | Germany | Participant |
| Siemens Aktiengesellschaft | Munchen | Germany | Participant |
| Barcelona Supercomputing Center Centro Nacional De Supercomputacion | Barcelona | Spain | Participant |
| Csc-Tieteen Tietotekniikan Keskus Oy | Espoo | Finland | Participant |
| Commpla SRL | Pisa | Italy | Third party |
| Consiglio Nazionale Delle Ricerche | Roma | Italy | Participant |
| Politecnico Di Torino | Torino | Italy | Participant |
| Trust-It Services SRL | Pisa | Italy | Participant |
| Gard AS | Arendal | Norway | Associatedpartner |
| Meteorologisk Institutt | Oslo | Norway | Participant |
| European Centre for Medium-Range Weather Forecasts | Reading | United Kingdom | Participant |
Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI