Empowering weather and climate forecast
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
Hamilton gets Medal of Freedom from Obama
MAELSTROM thinks that both female and male brains should help shape our future.
Yet more obstacles than we thought prevent women from achieving in science.
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
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
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


Survey on our apps and datasets now open

2023-11-07, Jan Mirus

How are we doing? We're collecting feedback. How useful are our apps and datasets? How easy is it to access them and work with them? Please take the time and complete our survey.

2023 workshop and bootcamp taking place next week – with audience from 59 countries!

2023-10-31, Jan Mirus

We will host our second workshop and second bootcamp next week at the premises of ECMWF in Reading, UK. We're thrilled to have gotten 242 registrations from 59 (!) countries on 6 continents!

Registration for our 2023 Dissemination Workshop closing tomorrow

2023-10-05, Jan Mirus

Hurry if you want to participate in our dissemination workshop on November 7th in Reading, UK or online.
Register here by tomorrow, 6th October.
The agenda is now online.

Introducing FZJ's AtmoRep

2023-08-29, Jan Mirus

This could become very influential:
Classical numerical models of the atmosphere exhibit biases due to incomplete process descriptions and they are computationally highly demanding. Recent AI-based weather forecasting models reduce the computational costs but lack the versatility of conventional models and do not provide probabilistic predictions.
The AtmoRep project asks if one can train one neural network that represents and describes all atmospheric dynamics. The FZJ team around Martin Schulz recently published a paper describing how this novel, task-independent stochastic computer model of atmospheric dynamics provides superior results for a wide range of applications: nowcasting, temporal interpolation, model correction, and counterfactuals.
Congrats to our MAELSTROM team members Bing Gong, Michael Langguth, Martin Schulz, and their FJZ colleagues!

Read the full paper here.
AtmoRep project page

Registration open!

2023-03-21, Jan Mirus

We're approaching two major events before MAELSTROM turns into the home stretch! The registration for both our second Dissemination Workshop and our second Boot Camp are open. Be sure to reserve your place.

See all news


Associated partners

See details