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.
- Magnetic imaging: Micro-flowers increase the local magnetic fieldMaterials with magnetic nanostructures have many potential applications such as in spintronics. To explore such materials, nanoscale magnetic-sensitive imaging techniques are very useful, but up to now only weak magnetic fields could be applied during the imaging process. Now an international collaboration led by Dr. Sergio Valencia, HZB, has developed an approach that overcomes this limitation. The team designed tiny magnetic flux concentrators (MFCs), into which the sample is placed. The geometry of the MFCs resembles a flower with a number of petals which focus the applied magnetic field into its center. This greatly expands the magnetic field range available during imaging, and so the range of magnetic systems that can be investigated. The micro-flowers, enhancing magnetic fields locally, can find application in different nanometric magnetic microscopy techniques.
- CIGS-perovskite tandem cell achieves record efficiency of 25.5 %A Berlin-based team from HZB and Center for the Science of Materials Berlin (CSMB) at the Humboldt-Universität zu Berlin has set a new record for a tandem solar cell. Using a combination of a CIGS semiconductor layer and perovskite, along with several optimised intermediate layers, they were able to convert 25.5% of sunlight into electrical energy. The previous record for this combination of materials and this size of cell stood at 24.6%. The new record has been certified and is visible in the prestigious Solar Cell Efficiency Tables (the "Green Tables"), which serve as the definitive ledger for the global photovoltaic community.
- Disorder creates new properties in compound semiconductorsAn international research team has demonstrated that the intrinsic disorder of the compound semiconductor CuInSnS₄ can be exploited to influence its optical properties. While the atomic vibrations also sense the local disorder, their response is averaged over many different local environments and therefore appear isotropic, as expected for a cubic crystal. In contrast, the optical excitations, known as excitons, are much more sensitive to the local arrangement of atoms. Surprisingly, they show a direction-dependent optical response even though the average crystal structure is cubic. These findings shed new light on the relationship between disorder and material properties, opening up new options for targeted 'disorder engineering' in optoelectronic and photocatalytic devices.