Machine Learning Demonstrator – Freshwater temperature

Main contractor: PropheSea

What is it? Global data centre facilities are projected to experience high water stress in the future. Critical industries such as thermal and nuclear power plants, data centers and chemical facilities are increasingly impacted by the more frequent and intense heatwaves in Europe. As surface water temperatures grow, these industries relying on freshwater for cooling face reduced efficiency, curtailments and regulatory constraints on thermal discharge. This Machine Learning demonstrator will harness the Climate Change Adaptation Digital Twin (Climate DT) and ML techniques to generate storyline-based freshwater temperature projections.

Concrete applications examples: Industries highly dependent on freshwater for cooling operations can perform predictions under different heatwave scenarios and better plan for alternative cooling technologies and long-term investment and policy decisions.

Main target end users: Data centers, nuclear and thermal power plants, chemical facilities relying on freshwater for cooling operations.

Climate DT data for planning freshwater cooling operations

PropheSea, experts in AI-powered optimisation software for energy related applications, is the prime contractor for the initiative, supported by the Royal Meteorological Institute of Belgium (RMI) and Antea Group.

The Belgian national weather service RMI contributes the expertise in meteorology and climate, storyline development, quality assurance and the ML algorithm development. Antea Group, a leading international environmental and engineering consultant, ensures stakeholder engagement, the environmental impact and end-user validation, through a core user group including main industry actors.

The demonstrator will develop an ML application enabling users to explore different scenarios of heatwave impacts and freshwater temperatures based on the high-resolution data of the Climate DT and integrating site-specific data to forecast freshwater surface temperatures at high spatial and temporal fidelity. The shift from static to dynamic scenario-based resilience planning for the long-term is made possible by the combination of Climate DT and state-of-the-art machine learning techniques. The system can reflect local conditions more accurately than standard models.

The application complements and expands existing demonstrators and services creating synergies with other DestinE projects offering a clear added value through economic and operational benefits for industrial users and environmental protection.

ECMWF, as a key implementing entity of the Destination Earth initiative of the European Union, has issued a series of pilot services 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 services 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.