Dresden 2020 – wissenschaftliches Programm

Die DPG-Frühjahrstagung in Dresden musste abgesagt werden! Lesen Sie mehr ...

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

O: Fachverband Oberflächenphysik

O 25: Poster Session - Focus Sessions: Innovation in Machine learning PRocEsses for Surface Science (IMPRESS)

O 25.2: Poster

Montag, 16. März 2020, 18:15–20:00, P1A

Classification of grazing incidence x-ray diffraction patterns using neural networks — •Verena Eslbauer, Johannes J. Cartus, Roland Resel, and Oliver T. Hofmann — Institute of Solid State Physics, NAWI Graz, Graz University of Technology, Austria

Grazing incidence X-ray diffraction is a frequently used tool to investigate the crystalline properties of thin films. Hereby, indexing Bragg peaks is a fundamental procedure for phase analysis and detection of unknown polymorphs. The current solution is an iterative approach, which is both tedious and requires the knowledge of an experienced material scientist. We are currently developing a software based on convolutional neural networks that should enable automatic classification of crystal systems. We have created a large set of crystal structures with pre-determined symmetries and their diffraction patterns. These serve as a training dataset for our convolutional neural network. At the current status of our work we can differentiate between different crystal systems, independent of the preferred orientation of their crystallites.

The next steps of our research involve the assignment of Laue indices to Bragg peaks and finally the determination of the lattice constants of the crystallographic unit cell.