BMFTR funding for astrophysical research networkAI models for many data sources and tasks
16 December 2025

Photo: UHH/Private
The Federal Ministry of Research, Technology and Space is providing 3 million euros in funding for a research project on AI-supported analysis of large amounts of data in astrophysics and particle physics. SciFM is coordinated by Prof. Dr. Luisa Lucie-Smith, principal investigator at the Cluster of Excellence “Quantum Universe” at the University of Hamburg.
Physical theories can currently only explain a fraction of the universe. Ninety-five percent of all energy in the universe eludes scientific analysis. The nature of this so-called “dark energy” or “dark matter” can only be theorized about at this point.
Experiments at particle accelerators and observations made using modern telescopes provide data that should enable answers based on experiments and observations. “Artificial intelligence opens up new possibilities for us in penetrating the huge amounts of data obtained in this way,” explains astrophysicist Luisa Lucie-Smith. She coordinates the project, which aims to develop a new generation of advanced AI tools, known as foundation models.
“Instead of training smaller, specialized models for individual tasks, we want to use the Foundation models to create AI generalists that are trained on data from a variety of sources and can solve many different tasks,” explains Prof. Dr. Gregor Kasieczka from the University of Hamburg, who is also part of the project team. The new models could be used, for example, to create comprehensive full-sky maps of the universe based on telescope observations at different wavelengths. Or they could be trained on so-called jet events and shower particles from particle physics experiments such as those at the Large Hadron Collider at CERN.
In addition to the University of Excellence in Hamburg, the Ludwig Maximilian University of Munich (LMU), the Technical University of Munich (TUM), the University of Heidelberg, and RWTH Aachen University are also involved in SciFM. The BMFTR is funding SciFM as part of the “ErUM Data” action plan.

