5 papers · 1 filter
Broken neural scaling laws in materials science
Max GroÃmann, Max Großmann, Malte Grunert +1
In materials science, data are scarce and expensive to generate, whether computationally or experimentally. Therefore, it is crucial to identify how model performance scales with d…
Many-body perturbation theory vs. density functional theory: A systematic benchmark for band gaps of solids
Max GroÃmann, Marc Thieme, Malte Grunert +1
We benchmark many-body perturbation theory against density functional theory (DFT) for the band gaps of solids. We systematically compare four variants using…
On the origin of bulk-related anisotropies in surface optical spectra
Max GroÃmann, Kai Daniel Hanke, Chris Yannic Bohlemann +4
Reflection anisotropy spectroscopy (RAS) is a powerful method for probing the optical properties of surfaces, used routinely in research and industrial applications, yet the origin…
Discovery of sustainable energy materials via the machine-learned material space
Malte Grunert, Max GroÃmann, Erich Runge
Does a machine learning model actually gain an understanding of the material space? We answer this question in the affirmative on the example of the OptiMate model, a graph attenti…
Deep learning of spectra: Predicting the dielectric function of semiconductors
Malte Grunert, Max GroÃmann, Erich Runge
Predicting spectra and related properties such as the dielectric function of crystalline materials based on machine learning has a huge, hitherto unexplored, technological potentia…