Empowering weather and climate forecast
MAELSTROM co-design cycle
To strengthen high-performance computing and weather and climate prediction in Europe, MAELSTROM will enhance the use of machine learning in Earth system science via concerted developments of machine learning, software and hardware tools in a so-called co-design cycle.
Read more
planet earth climate
MAELSTROM develops new machine learning applications in weather and climate science that can exploit exaflop performance.
MAELSTROM delivers benchmark datasets to allow for a quantitative intercomparison of machine learning tools — serving as blueprints for many machine learning applications in Earth system science.
Read more
weather event
MAELSTROM develops software environments to build exascale-ready machine learning tools that can be used within weather and climate science and beyond.
Read more
HPC system
MAELSTROM develops compute system designs that are optimised for machine learning applications for weather and climate predictions at the node and system level.
MAELSTROM will transfer this knowledge to machine learning applications in other domains to optimise the use of future EuroHPC systems.
Read more


Five datasets ready for download and public use

2021-09-01, Jan Mirus

We're excited to have reached a big milestone end of August: a series of datasets went public. Dataset for energy production forecast
Dataset for 2m temperature downscaling
Dataset for ensemble predictions
Datasets for 2m temp. and precipitation short-range forecasts
Dataset to emulate radiation
Feedback and comments will be much appreciated.

How MAELSTROM will change weather & climate prediction

2021-07-08, Peter Dueben

Why is project MAELSTROM urgently needed, and how will it impact weather & climate prediction, machine learning and supercomputing? Read in ECMWF's science blog how MAELSTROM will radically change W&C predition with new ML tools, HPC-ready development platforms for data scientists and high-performance compute system designs: ECMWF Science Blog

New paper to show that machine learning can improve the representation of gravity waves within weather models

2021-06-17, Peter Dueben

A paper on physics emulation using machine learning has been accepted for publication in the Journal of Advances in Modelling of the Earth System (JAMES). This work creates a MAELSTROM dataset to emulate a piece of ECMWF’s weather forecast model and will feature in JAMES as part of a new special collection on using machine learning for earth system modelling. The work emulates the parametrisation of non-orographic gravity wave drag (NOGWD), a key physical process in the accurate modelling of stratospheric winds and temperatures. Using neural networks we accurately emulate this physical process even over long simulation periods and by using a high-fidelity reference scheme, we are able to improve prediction quality when compared to the standard scheme. Creating and publishing a dataset will enable other researchers to test machine learning methods and seek to produce even better emulators. More information

Learn about machine learning for weather forecasting at ISC2021

2021-06-08, Peter Dueben

At ISC 2021 - one of the largest virtual community get togethers for high performance computing (HPC), machine learning (ML) and high performance data analytics (HPDA) - MAELSTROM member Peter Dueben has chaired a focus session on machine learning for weather forecasting. Here, Jason Hickey from Google Research provided an overview on the latest developments of machine learning applications for now-casting, MAELSTROM member Martin Schultz from Forschungszentrum Juelich talked about whether bigger is always better for deep learning applications in air quality, and Duncan Watson-Parris from the University of Oxford showed us results on the emulation of climate models. More information

MAELSTROM was successfully kicked-off (virtual)

2021-04-14, Jan Mirus

The MAELSTROM project has been kicked-off via a virtual meeting. The meeting started with a short talk by our Project Officer Daniel Opalka and continued with presentations and discussions of the different work packages. The public had the opportunity to learn more about the project during a public plenary presentation. The recording of the presentation can be found here.

See all news


Associated partners

See details