Destination Earth digital twin to improve AI climate and weather predictions
en-GBde-DEes-ESfr-FR

Destination Earth digital twin to improve AI climate and weather predictions


An agreement on the third implementation phase of Destination Earth (DestinE), the European Commission’s initiative to develop a highly accurate digital twin of the Earth, has been signed between the European Commission and the European Centre for Medium-Range Weather Forecasts (ECMWF). The third phase will start in June 2026 and end in June 2028.

The DestinE digital twins enable the exploration of past, present and likely future climate and extreme conditions, including tailored ‘what if’ scenarios, such as Storyline simulations to replay past events and explore how they might unfold in a world 2 °C warmer. These help European and national institutions understand and better prepare for, and adapt to, risks caused by extreme weather and climate change.

Roberto Viola, Director-General of the DG for Communications Networks, Content and Technology, European Commission, said:

“Destination Earth demonstrates how Europe can transform major investments in supercomputing and artificial intelligence into concrete benefits for its citizens. By uniting world-class EuroHPC infrastructure, cutting-edge AI Factories, and Europe's unparalleled expertise in climate and weather science, DestinE strengthens our collective capability to anticipate climate and weather threats — and to act decisively on them. This is how Europe builds resilience.”

Since 2022, ECMWF has worked closely with ESA, EUMETSAT and more than 100 partner organisations, including many national meteorological services, to implement the Climate Change Adaptation Digital Twin and the Weather-Induced Extremes Digital Twin.

These core components of DestinE have already progressed from early prototypes to modelling frameworks that routinely produce high-resolution climate projections and detailed simulations of extreme events. 

As a key element of the DestinE system, ECMWF and its partners have also implemented the Digital Twin Engine that orchestrates the digital twin workflows and data flows on EuroHPC supercomputers and DestinE infrastructure and enables tailored access to high-resolution digital twin data across the whole system.

Since 2024 (Phase 2), DestinE has also seen a substantial expansion of artificial intelligence activities, including the development of machine-learning components for different parts of the Earth system (land, ocean, sea ice, waves and hydrology), and AI-based solutions that enhance interactivity with digital twin data.  

In Phase 3, ECMWF and its partners will focus on operating and interlinking the Climate and Extremes Digital Twins, and the Digital Twin Engine, and developing the AI capabilities further:

“Phase 3 allows us to consolidate the digital twins while taking the next major steps towards delivering an AI Earth-system model, building on the combined expertise of ECMWF, our Member States and partners”, said Florian Pappenberger, Director-General of ECMWF.

“By integrating physical understanding with innovative AI approaches, we will further enhance Europe’s weather and climate prediction capabilities”, he added.

“This will support European National Meteorological and Hydrological Services and other public institutions in preparing for extreme events in a changing climate and protecting communities. At the same time, the combination of high-resolution, AI-ready digital twin datasets and Europe’s AI ecosystem—including the AI Factories —creates the conditions for a new generation of AI applications for weather and climate and supports innovation across European industry and the public sector. Together, these developments strengthen Europe’s leadership in trustworthy AI for environmental intelligence, while supporting preparedness, resilience and innovation across Europe.”

The developments include advancing and coupling machine learning based Earth system components towards an AI Earth system model that complements physics-based simulations and supports uncertainty quantification and rapid ‘what-if’ experimentation.

It also includes producing high quality, AI-ready datasets that can feed Europe’s AI Factories, strengthening links between supercomputing, AI and Earth-system science. 

Together, these developments will continue to leverage Europe’s investment in high-performance computing and artificial intelligence and complement existing national and European services, developed in close collaboration with Member States. 

Irina Sandu, Director of Destination Earth at ECMWF, said: 

“Destination Earth is, above all, a collaborative European effort. It brings together expertise in Earth system modelling, software engineering, high-performance computing, and artificial intelligence. By pooling resources and working closely with our partners, we are building capabilities that complement existing national and European services and help European institutions and Member States prepare for the challenges posed by climate change and extreme events.” 

-ends-

Attached files
  • Image 1 - A view of the Digital Twin: an ultra high resolution 5 km simulation from the European Union’s Destination Earth initiative, visualising global cloud systems through liquid and ice water distribution with unprecedented clarity. Created by Andreas Mueller, ECMWF in the framework of the European Union Destination Earth Initiative with acknowledgement to EuroHPC Joint Undertaking. Credit: ECWMF Destination Earth
  • Image 2 - The digital twin: a global view of 2 m temperatures and 10 m wind speeds, where colour brightness reflects wind intensity. This high-resolution rendering blends scientific data with atmospheric effects and city night lights. Created by Andreas Mueller, ECMWF in the framework of the European Union Destination Earth Initiative with acknowledgement to EuroHPC Joint Undertaking. Credit: ECWMF Destination Earth
Regions: Europe, United Kingdom
Keywords: Science, Climate change, Environment - science

Disclaimer: AlphaGalileo is not responsible for the accuracy of content posted to AlphaGalileo by contributing institutions or for the use of any information through the AlphaGalileo system.

Testimonials

For well over a decade, in my capacity as a researcher, broadcaster, and producer, I have relied heavily on Alphagalileo.
All of my work trips have been planned around stories that I've found on this site.
The under embargo section allows us to plan ahead and the news releases enable us to find key experts.
Going through the tailored daily updates is the best way to start the day. It's such a critical service for me and many of my colleagues.
Koula Bouloukos, Senior manager, Editorial & Production Underknown
We have used AlphaGalileo since its foundation but frankly we need it more than ever now to ensure our research news is heard across Europe, Asia and North America. As one of the UK’s leading research universities we want to continue to work with other outstanding researchers in Europe. AlphaGalileo helps us to continue to bring our research story to them and the rest of the world.
Peter Dunn, Director of Press and Media Relations at the University of Warwick
AlphaGalileo has helped us more than double our reach at SciDev.Net. The service has enabled our journalists around the world to reach the mainstream media with articles about the impact of science on people in low- and middle-income countries, leading to big increases in the number of SciDev.Net articles that have been republished.
Ben Deighton, SciDevNet

We Work Closely With...


  • e
  • The Research Council of Norway
  • SciDevNet
  • Swiss National Science Foundation
  • iesResearch
Copyright 2026 by AlphaGalileo Terms Of Use Privacy Statement