Destination Earth is a European Union-funded initiative that aims to build a digital replica of the Earth system by 2030. The project integrates climate change adaptation and weather-induced extreme events with AI capabilities, providing flexible simulation frameworks for tailored information on impacts and potential evolutions.
The ECMWF's global forecasting system now incorporates new cloud radar data from the ESA-JAXA EarthCARE space mission, enhancing weather forecasting accuracy. This move is expected to improve predictions for extreme weather events like typhoons and heavy rainfall.
The European Centre for Medium-Range Weather Forecasts (ECMWF) has appointed two Deputy Director-Generals to strengthen its leadership in delivering world-leading science and operational weather services. Dr Jørn Kristiansen will lead the Forecast Department, while Dr Irina Sandu will lead the Research Department.
A new El Niño index compares warming in the central Pacific with temperatures across the wider tropics, providing a clearer picture of unusual conditions. The Relative Niño index is more suited for monitoring and comparing events over time, reducing sensitivity to global warming trends.
The European Centre for Medium-range Weather Forecasts (ECMWF) is upgrading its key forecasting systems, the Integrated Forecast System (IFS) and the Artificial Intelligence/Integrated Forecasting System (AIFS), to improve weather forecast accuracy. The upgrades include enhancements to ocean- sea ice interactions, wave forecasts, and s...
A machine learning technique identifies optimal spots for tree planting to inform climate mitigation strategies. Optimised afforestation can reduce river peaks by up to 43% while preserving groundwater by up to 60%. The study's findings highlight the importance of data-driven technologies in supporting large-scale, smarter planning.
MicroEnsemble wins AI Weather Quest, demonstrating improved sub-seasonal weather forecasting accuracy. The team uses AI technologies to post-process state-of-the-art forecasts, achieving consistent performance across various weather variables.
The OpenIFS model, a portable version of the global forecasting model used by ECMWF, is now available for all, making it easier to collaborate and generate new ideas. The change will support reproducible research and keep users current with the latest updates.
The European Centre for Medium-Range Weather Forecasts (ECMWF) is launching its 2026 climate and weather data challenges to improve rapid decision-making during wildfires, explore flood forecast data from 10,000 stations globally, and detect implausible behavior in machine learning. The deadline for applications is April 9, 2026.
The European Commission and ECMWF have signed an agreement for the third implementation phase of DestinE, a digital twin project aiming to improve AI climate and weather predictions. The project will start in June 2026 and focus on operating and interlinking digital twins, as well as developing AI capabilities further.
The new ECMWF Director-General, Florian Pappenberger, emphasizes the importance of collaboration, innovation, and people-centric approaches. He plans to leverage high-performance computing, AI, and data assimilation to advance weather and climate prediction.
The European Centre for Medium-Range Weather Forecasts (ECMWF) and several National Meteorological Services across Europe have been honored with the 2025 HPCwire Readers’ and Editors’ Choice Award for
ECMWF is poised to unveil a new phase in its data sharing strategy, providing the complete ECMWF Real-time Catalogue under a Creative Commons licence. The organization will make its forecast data free and open at a 25 km resolution in real time with no latency, starting from October 1st.
Dr Florian Pappenberger will lead ECMWF starting January 2026, building on AI and machine learning tools co-developed with Member States. He aims to strengthen partnership across all Member States and the European Meteorological Infrastructure.
The new AIFS ENS model outperforms state-of-the-art physics-based models, with gains of up to 20%, and generates forecasts over 10 times faster while reducing energy consumption by approximately 1,000 times. This complements ECMWF's portfolio by leveraging machine learning and artificial intelligence.
The new Probability of Fire model incorporates multiple data sources beyond weather to refine predictions, providing a more holistic approach. Traditional weather-based fire danger indices often fail to pinpoint areas at risk of ignition with enough specificity, but ML can help.
The European Centre for Medium-Range Weather Forecasts (ECMWF) has launched an Artificial Intelligence Forecasting System (AIFS), providing the greatest granularity in weather prediction models. The AIFS outperforms state-of-the-art physics-based models, achieving gains of up to 20% in tropical cyclone tracks.