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

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

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 1: AKPIK Talks

AKPIK 1.2: Vortrag

Montag, 16. März 2020, 17:00–17:15, HSZ 301

Fast fitting of reflectivity data of growing thin films using neural networks — •Alessandro Greco1, Vladimir Starostin1, Christos Karapanagiotis2, Alexander Hinderhofer1, Alexander Gerlach1, Linus Pithan3, Sascha Liehr4, Frank Schreiber1, and Stefan Kowarik41Institut für Angewandte Physik, University of Tübingen, Auf der Morgenstelle 10, Tübingen 72076, Germany — 2Institut für Physik, Humboldt Universität zu Berlin, Newtonstrasse 15, Berlin 12489, Germany — 3European Synchrotron Radiation Facility, 71 Avenue des Martyrs, Grenoble 38000, France — 4Bundesanstalt für Materialforschung und -prüfung (BAM), Unter den Eichen 87, Berlin 12205, Germany

X-ray reflectometry is a powerful and popular scattering technique that can give valuable insight into the structure and growth behavior of thin films. This study [1] shows how a simple artificial neural network model can be used to determine the thickness, roughness and electron density of thin films of different organic semiconductors [diindenoperylene, copper(II) phthalocyanine and α-sexithiophene] on SiO2 from their reflectivity data with millisecond computation time and with minimal user input or a priori knowledge. For a large experimental data set of 372 XRR curves, it is shown that a simple fully connected model can provide good results with a mean absolute percentage error of 8–18% when compared with the results obtained by a genetic least mean squares fit using the classical Parratt formalism. Furthermore, current drawbacks and prospects for improvement are discussed.

[1] Greco et al., J. Appl. Cryst. (2019). 52, 1342–1347

100% | Bildschirmansicht | English Version | Kontakt/Impressum/Datenschutz
DPG-Physik > DPG-Verhandlungen > 2020 > Dresden