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

MM: Fachverband Metall- und Materialphysik

MM 33: Topical session (Symposium MM): Big Data Analytics in Materials Science

MM 33.7: Vortrag

Donnerstag, 4. April 2019, 12:30–12:45, H43

Neural-network representation of materials for robust crystal-structure recognition — •Andreas Leitherer, Angelo Ziletti, Matthias Scheffler, and Luca M. Ghiringhelli — Fritz Haber Institute of the Max Planck Society, Berlin, Germany

Assigning the crystal structure to local regions of large atomic structures can reveal hidden patterns and thus interesting material properties. Available computational methods either support a large number of space groups but show critically limited robustness, or are very robust but can treat only a handful of classes. We use neural networks to robustly assign the correct crystal-structure type to a given material while being able to treat numerous space groups and chemical species. To capture information about the local chemical environments, we apply the smooth-overlap-of-atomic-positions (SOAP) descriptor, serving as input to the deep-learning model. Since the neural network provides an intrinsic similarity metric, we are able to investigate structural transitions such as the Bain path between face-centered cubic and body-centered cubic structures. We also discuss the application of our framework to detect precipitates in Ni-based superalloys (materials used in aircraft engines), whose structure is usually experimentally investigated via atom probe tomography. Finally, we show that the neural network automatically learns how to map crystal structures to a meaningful low-dimensional manifold, an ability which we exploit by building easily interpretable structural-similarity maps.