The European Centre for Medium-Range Weather Forecasts and its international partners have been recognised with two honours in the 23rd edition of the HPCwire Readers’ Choice Awards, presented at the 2026 International Conference for High Performance Computing, Networking, Storage, and Analysis in Chicago, Illinois. Announced during the SC26 conference at the HPCwire booth and via its digital publication platform, the annual honors acknowledge collaborative achievements in applying high-performance computing and artificial intelligence architectures to atmospheric science and societal challenges.
In the category of Best Use of HPC/AI in Physical Sciences, ECMWF and partner national meteorological services across Europe were recognized for their deployment of Anemoi, a jointly developed open-source artificial intelligence software framework. By pairing this framework with EuroHPC supercomputers—including LUMI, MN5, Leonardo, and JUPITER—the institutions are training data-driven models at scale to operationalize a new generation of weather prediction tools that allow individual meteorological agencies to tailor automated forecasts to specific regional requirements.
Development of the Anemoi software framework involves an extensive network of national meteorological services working alongside ECMWF. Participating European institutions include Spain’s Agencia Estatal de Meteorología, the Danish Meteorological Institute, Germany’s Deutscher Wetterdienst, the Finnish Meteorological Institute, GeoSphere Austria, the Latvian Environment, Geology and Meteorology Centre, the Royal Netherlands Meteorological Institute, Ireland’s Met Éireann, Météo-France, Switzerland’s Federal Office of Meteorology and Climatology, the Norwegian Meteorological Institute, the Royal Meteorological Institute of Belgium, the Swedish Meteorological and Hydrological Institute, and the United Kingdom Met Office.
ECMWF and its collaborators secured a second honour for Best Use of HPC/AI in Response to Societal Plight through the deployment of Forecast-in-a-Box. Developed in partnership with the Norwegian Meteorological Institute, the World Meteorological Organization, and Malawi’s Department of Climate Change and Meteorological Services, the system operates as a portable end-to-end forecasting pipeline designed to bring advanced predictive modeling to regions with limited local computational infrastructure.
The Forecast-in-a-Box package was co-developed under the European Union’s flagship Destination Earth initiative to make state-of-the-art forecasting easier to run locally, thereby reinforcing early warning capabilities. Roar Skålin, Director General of MET Norway, emphasized that the deployment demonstrates practical artificial intelligence delivery directly into the hands of national meteorological services, while Dr. Lucy Mtilatila, Director and Permanent Representative with the WMO for the Malawi Met Service, noted that multilateral cooperation and shared technological advancements remain vital for addressing climate vulnerabilities.
The honours represent the third consecutive year that ECMWF initiatives have received distinction at the annual supercomputing conference. Irina Sandu, Deputy-Director General and Director of Science and Innovation at ECMWF, stated that combining scientific expertise with shared computing resources and open innovation enables capabilities beyond the reach of individual organizations, while Ioan Hadade, Team Lead for HPC applications at ECMWF who accepted the honours in Chicago, affirmed that the awards reflect sustained institutional momentum in advancing computational meteorology.
Roberto Viola, Director-General of DG CONNECT at the European Commission, highlighted the strategic integration of world-class supercomputing infrastructure with artificial intelligence under Destination Earth. Viola stated that the development of ultra-high-resolution digital twins and Earth system artificial intelligence models across EuroHPC systems equips scientists and decision-makers with tools to anticipate climate risks and formulate targeted adaptation strategies.
The HPCwire Readers’ and Editors’ Choice Awards are decided through a global nomination and voting process conducted across the high-performance computing community in combination with selections by publication editors. Tom Tabor, Chief Executive Officer of TCI Media, noted that as HPCwire marks 38 years of industry coverage, the confluence of high-performance computing and artificial intelligence continues to accelerate scientific discovery and highlight critical technical work that often operates outside public visibility.
As an intergovernmental organization supported by 35 Member and Co-operating States, ECMWF operates a continuous 24/7 research and operational forecasting facility dedicated to numerical weather prediction. The center focuses on medium- and long-range atmospheric forecasts while maintaining extensive meteorological data repositories, including the ERA5 reanalysis dataset funded through the European Union Copernicus programme.
The broader technological framework supporting these award-winning applications relies on collaborative European digital initiatives launched in 2022. Destination Earth is managed under DG CNECT across three entrusted entities—ECMWF for the initial digital twins and Digital Twin Engine, the European Space Agency for the platform architecture, and EUMETSAT for data lake operations—supported by over 120 partner organizations, alongside the EuroHPC Joint Undertaking comprising the European Commission and 39 participating states.
By utilizing the Anemoi software framework, meteorological services leverage EuroHPC supercomputers—specifically LUMI, MN5, Leonardo, and JUPITER—to train AI models at scale. These capabilities make it possible to train AI models at scale and allow meteorological services to tailor forecasts to their specific needs. The EuroHPC Joint Undertaking brings together the European Union and participating countries to coordinate efforts and pool resources with the objective of making Europe a world leader in supercomputing, with a governing board comprising representatives from the European Commission and 39 participating states.
The Forecast-in-a-Box initiative brings state-of-the-art AI weather forecasting to countries with limited computing resources. By co-developing this solution under the European Union’s Destination Earth initiative, the project enables a portable, end-to-end forecasting pipeline that simplifies the deployment of advanced AI models. This solution offers a portable end-to-end forecasting pipeline that makes advanced AI models easier to deploy and run locally. The implementation of this pipeline directly strengthens early warning and national forecasting capacity. This initiative reflects multilateral cooperation and effective partnerships, demonstrating the strength in shared technological advancements for the global good by making forecasting more accessible.
Destination Earth, launched in 2022, serves as the overarching framework for these advancements, functioning as an ambitious, long-term project to construct a precise digital replica of the Earth system. The initiative is implemented by three entrusted entities: ECMWF is responsible for creating the first two digital twins and the Digital Twin Engine, the European Space Agency is responsible for building the DestinE Platform, and EUMETSAT is responsible for creating the Data Lake. Involving over 120 partner organisations from across Europe, the initiative builds ultra-high-resolution digital twins and AI models of the Earth system on EuroHPC infrastructure to provide decision-makers and scientists with capabilities to anticipate climate risks and shape adaptation strategies.
ECMWF itself operates as an intergovernmental organization with a mandate to deliver high-quality numerical weather predictions for its 35 Member and Co-operating States. ECMWF's research and operational center operates 24/7, focusing on medium- and long-range forecasts, and maintains one of the world's largest meteorological data archives, including ERA5, funded by the EU Copernicus programme. The center's mission is to deliver global numerical weather predictions focusing on the medium-range and monitoring of the Earth system to and with its Member States.
The recognition afforded by the HPCwire Awards, now in its 23rd edition, underscores the growing intersection between high-performance computing, artificial intelligence, and applied science. As HPCwire marks 38 years of covering high-performance computing, the awards celebrate the people, organizations, and innovations driving progress as HPC and AI accelerate discovery across science and industry. The awards help bring these achievements to light, recognizing the depth, ingenuity, and impact of high-performance computing innovation across the globe.
Subject of Research: High-performance computing and artificial intelligence frameworks for global and regional weather forecasting
Article Title: News release: ECMWF receives honors in 2026 HPCwire readers’ and editors’ choice awards
Article References: News release: ECMWF receives honors in 2026 HPCwire readers’ and editors’ choice awards. Original publication (Bibliographic details unavailable.)
Image Credits: AI Generated
DOI: Not provided
Keywords: ECMWF, HPCwire Readers Choice Awards, Anemoi, Forecast-in-a-Box, Destination Earth, EuroHPC JU, Weather Forecasting, Artificial Intelligence, Supercomputing, LUMI, Leonardo Supercomputer, MareNostrum 5, JUPITER Supercomputer, MET Norway, Malawi Met Service, Numerical Weather Prediction, Early Warning Systems, Digital Twins
Cite Scienmag News
Blake Davidson. (November 17, 2026). ECMWF Receives Two 2026 HPCwire Awards for Collaborative Artificial Intelligence Forecasting. Scienmag. https://scienmag.com/ecmwf-receives-two-2026-hpcwire-awards-for-collaborative-artificial-intelligence-forecasting/
Blake Davidson. "ECMWF Receives Two 2026 HPCwire Awards for Collaborative Artificial Intelligence Forecasting." Scienmag, 17 November 2026, https://scienmag.com/ecmwf-receives-two-2026-hpcwire-awards-for-collaborative-artificial-intelligence-forecasting/. Accessed 17 November 2026.
Blake Davidson. "ECMWF Receives Two 2026 HPCwire Awards for Collaborative Artificial Intelligence Forecasting." Scienmag. November 17, 2026. https://scienmag.com/ecmwf-receives-two-2026-hpcwire-awards-for-collaborative-artificial-intelligence-forecasting/








