Following Destination Earth’s co-design approach, the European Centre for Medium-Range Weather Forecasts (ECMWF) has contracted development of a series of Machine Learning Demonstrators and Pilot Services that are now starting. The projects now contracted include a broad range of sectors that are highly dependent on climate and weather information.
With these actions, ECMWF, as one of the key implementing entities of Destination Earth, the ambitious initiative of the European Commission to create a digital replica of different aspects of the Earth system, aims to demonstrate the added value of the Weather-Induced Extremes Digital Twin (Extremes DT) and the Climate Change Adaptation Digital Twin (Climate DT) and engage potential users in co-design.
Some of the Pilot Services build on the previous work achieved in Use Cases developed during Phase I of DestinE (2022-2024). Both the Pilot Services and the ML Demonstrators involve specific groups of users in the development and will result in applications and interfaces available for target user groups, building on data from the Climate DT and/ or the Extremes DT and other data sources relevant for the sectors involved.
The key target users involved in these Pilot Services and Machine Learning demonstrators are from sectors most impacted by climate change and weather extremes like maritime operations, coastal areas, renewable energy, agriculture, environment and urban planning among others.
The Pilot Services selected are:
High Resolution Forecasts for Next Generation Dynamic Line Rating Computation
The objective is using high spatial and temporal resolution data from the Extremes DT for improving Dynamic Line Rating (DLR) energy transmission applications. Read more
Main contractor: KMI, (Koninklijk Meteorologisch Instituut van België) Royal Meteorological Institute of Belgium.
High-Resolution Precipitation-to-Flood Signals
The project will provide flood information for the Italian territory using high spatial and temporal resolution data from the Extremes DT combined with hydrological models and the ICON model. Read more
Main contractor: Agenzia ItaliaMeteo (Italy)
Marine Safety for the Energy Industry
Combining data from the Extremes DT global and on-demand components, FMI and its partner Met Norway will provide enhanced wave and vessel icing forecasts for the Arctic. Read more
Main contractor: Finnish Meteorological Institute (FMI)
Global Tide and Surge Forecast, Global Ship Route Optimization
This pilot service will combine data from the Extremes DT and Deltares’ Global Tide and Surge Model (GTSM) and the Global Storm Surge Information System (GLOSSIS), to develop a global tide and surge forecast and a global ship route optimization system. Read more
Main contractor: Deltares (Netherlands)
Urban heat – Bringing climate insights to the neighbourhood scale
Based on data from the Climate DT with advanced urban climate models to deliver local climate information, this Pilot Service will develop a service delivering climate and urban heat data at 100-200 meters spatial resolution – the scale where impacts are truly felt.
Main contractor: VITO Vlaamse Instelling voor Technologisch Onderzoek, Flemish Institute for Technological Research (Belgium)
Supporting European Farmers’ Decisions in Perennial Agriculture through DestinE solutions
Using data from the Climate DT the project will provide climate information tailored to the specific needs of agriculture in the Italian region of Trentino.
Main contractor: Amigo S.R.L (Italy)
As part of the implementation of machine learning and artificial intelligence techniques during the second phase of Destination Earth (2024-2026), a series of Machine Learning Demonstrators were selected:
Energy systems
DLR and its partners will use data from the Climate Change Adaptation Digital Twin (Climate DT) and state-of-the art energy grid models to train and validate an advanced machine learning (ML) system that will help optimise the power flow and resource allocation across the European electricity grid.
Main contractor: DLR, German Aerospace Center
Enhancing Forecast Precision and Data Usability with AI-based Multi-Model Data Fusion for DestinE
Combining the capabilities of the Destination Earth digital twins and the EuroHPC ecosystem, DWD will develop and demonstrate a machine learning system designed to integrate multiple model outputs into a single, optimised product.
Main contractor: DWD, Deutscher Wetterdienst, German meteorological service.
Machine learning for flood nowcasting
Using DestinE Extremes DT precipitation data, impact-based precipitation post-processing, hydrological models and advanced machine learning (ML) techniques, HydroLogic and its partners, the national meteorological service of the Netherlands (KNMI) and Weather Impact, aim to provide accurate flooding information. Read more
Main contractor: HydroLogic (Netherlands)
The Pilot Services and ML Demonstrators are expected to become accessible during 2026. Visit the DestinE Uses page for more information. New descriptions will be uploaded in the coming weeks in this article and on the page.
ECMWF, as a key implementing entity of the Destination Earth initiative of the European Union, has issued a series of Pilot Service contracts that demonstrate the added value of the Weather-Induced Extremes Digital Twin and the Climate Change Adaptation Digital Twin, and the wider DestinE architecture. The key target users of the Pilot Service are the sectors most impacted by climate change and weather extremes, such as maritime operations, coastal areas, energy, and more. The contracts include a specific call for machine learning and artificial intelligence-based proposals as a part of the implementation of ML/AI techniques within the Destination Earth initiative of the European Commission, led by DG CNECT, and implemented by ECMWF, EUMETSAT, ESA and over 100 partner institutions across Europe.
