With climate change being described as the greatest threat facing modern humans ever, it’s necessary to develop the tools needed to prepare for its potential future effects. Machine learning can help improve weather and climate modelling.
With that in mind, the EU-funded MAELSTROM project aims to improve European computer architecture to help evaluate future climate impacts. Specifically, it will advance compute system designs for optimal application performance and energy efficiency, a software framework to optimise usability and training efficiency for machine learning at scale, and large-scale machine learning applications for the domain of weather and climate science. Customised compute systems will be designed that are optimised for application needs to strengthen Europe’s high-performance computing portfolio.
- Project duration
- 1 Apr 2021 - 31 Mar 2024
- Project locations
- United Kingdom
- Project website
- https://www.maelstrom-eurohpc.eu/
Stakeholders
Coordinators
European Centre for Medium-Range Weather Forecasts (ECMWF)
- Address
- United Kingdom
- Website
- https://www.ecmwf.int/
Participants
European Centre for Medium-Range Weather Forecasts (ECMWF)
- Address
- United Kingdom
- Website
- https://www.ecmwf.int/
4Cast GmbH & Co. KG
- Address
- Germany
- Website
- https://4-cast.de/
E4 Computer Engineering SpA
- Address
- Italy
- Website
- https://www.e4company.com/
Eidgenössische Technische Hochschule Zürich (ETHZ)
- Address
- Switzerland
- Website
- https://ethz.ch/de.html
Forschungszentrum Jülich
- Address
- Germany
- Website
- https://www.fz-juelich.de
Meteorologisk institutt
- Address
- Norway
- Website
- https://www.met.no/
Université du Luxembourg
- Address
- Luxembourg
- Website
- https://wwwen.uni.lu/