University of Kassel and HZB establish Joint Lab for the use of artificial intelligence
View into the experimental hall of the electron accelerator BESSY II at Helmholtz-Zentrum Berlin. Researchers carry out experiments at approximately 50 beamlines. The aim of the cooperation between the University of Kassel and the HZB is to use artificial intelligence to evaluate these data more efficiently. © HZB/M. Setzpfand
The University of Kassel and Helmholtz-Zentrum Berlin are setting up a joint laboratory for the use of artificial intelligence, where they will be developing new experimental methods and improving the analysis of data from experiments performed at BESSY II.
Every year, nearly 3000 user groups from around the world visit the electron storage ring BESSY II to study an immense variety of materials using the brilliant X-ray light the ring generates. “In the research of current scientific problems, at BESSY II for example, so much data accumulates that it can barely be analysed using conventional analytical programs. In the Joint Lab, we will be developing and employing methods of artificial intelligence to do this analysis. These methods should even allow us to think up entirely new test scenarios in other scientific and technical areas that have always seemed beyond our analytical capabilities in the past,” says Prof. Dr. Arno Ehresmann, the vice president of the University of Kassel, who is also responsible for research funding.
HZB and the University of Kassel recently signed a joint cooperation agreement to set up the Joint Lab Artificial Intelligence Methods for Experiment Design (AIM-ED). A Joint Lab is a medium- to long-term form of cooperation established between the Helmholtz Association and universities. “We are pleased to be able to combine the expertise in artificial intelligence of the University of Kassel and Helmholtz-Zentrum Berlin in this way, for working on groundbreaking solutions together,” says Prof. Ehresmann.
One institute involved in the Joint Lab is the Kassel Research Center for Information System Design (ITeG). “There will also be several particularly strong research groups from the physics department working on the application of AI methods for the design, analysis or optimisation of experiments, including within a DFG Special Research Area,” Prof. Ehresmann says. The Intelligent Embedded Systems Group will also be involved, under the direction of Prof. Dr. Bernhard Sick, who has long been working intensively in the field of machine learning and artificial intelligence.
There are many synergies arising from the newly founded Joint Lab, emphasises Dr. Gregor Hartmann, a supervising researcher at Helmholtz-Zentrum Berlin. “The experiments at BESSY II generate immense amounts of data, where not only the volume of the data but also the complexity and understanding of their creation are decisive for good analysis.” HZB has great expertise in beamline development, and Prof. Ehresmann’s workgroup is contributing its expertise in detectors from the perspective of a long-term BESSY II user. The broad range of artificial intelligence methods covered by Prof. Bernhard Sick’s team will allow the best possible analysis of data. “I am very much looking forward to the intensive and exciting cooperation in this Joint Lab,” says Hartmann.
- Ultrafast demagnetisation - Thinner iron, stronger effectThe thinner an iron film, the more easily it can be demagnetised by a laser pulse. Researchers at the University of Duisburg-Essen, working with Helmholtz-Zentrum Berlin and other partners, have discovered why: the key lies in the magnetic order at the material's interfaces. In the long term, these findings could contribute to the development of new technologies for magnetic data storage. The results have been published in the scientific journal Advanced Science.
- Blind spot for the arrangement of atomsArtificial intelligence is increasingly being used to predict the properties of new materials. A research team from Jena and the United States now shows in a study published in the journal Nature Computational Science that when language models are used for this purpose, they reliably identify which types of atoms a material contains. However, they make insufficient use of information about how those atoms are arranged in space. Neither larger models nor additional training data resolve this weakness. For material properties that depend strongly on structure, AI models specifically designed to process spatial relationships are therefore the more reliable choice. (DOI: 10.1038/s43588-026-01045-2)
- Patterns of polar vortices in lead-free superlattices on siliconA team at HZB has, for the first time, reported polar vortices in (BaTiO3/SrTiO3)10 superlattices on silicon. These results expand the range of materials and substrates on which polar topological textures can occur and open up new options for incorporating complex ferroelectric states into silicon-based technologies.