Fast fitting of reflectivity data of growing thin films using neural networks
Starostin, Vladimir
Karapanagiotis, Christos
Hinderhofer, Alexander
Gerlach, Alexander
Pithan, Linus
Liehr, Sascha
Schreiber, Frank
Kowarik, Stefan
DOI: https://doi.org/10.1107/S1600576719013311
Persistent URL: http://resolver.sub.uni-goettingen.de/purl?gldocs-11858/8746
Starostin, Vladimir; 1Institut für Angewandte Physik, University of Tübingen, Auf der Morgenstelle 10, Tübingen72076, Germany
Karapanagiotis, Christos; 2Institut für Physik, Humboldt Universität zu Berlin, Newtonstrasse 15, Berlin12489, Germany
Gerlach, Alexander; 1Institut für Angewandte Physik, University of Tübingen, Auf der Morgenstelle 10, Tübingen72076, Germany
Pithan, Linus; 3ESRF The European Synchrotron, 71 Avenue des Martyrs, Grenoble38000, France
Liehr, Sascha; 4Bundesanstalt für Materialforschung und -prüfung (BAM), Unter den Eichen 87, Berlin12205, Germany
Abstract
X‐ray reflectivity (XRR) is a powerful and popular scattering technique that can give valuable insight into the growth behavior of thin films. This study shows how a simple artificial neural network model can be used to determine the thickness, roughness and density of thin films of different organic semiconductors [diindenoperylene, copper(II) phthalocyanine and α‐sexithiophene] on silica from their XRR 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.
Artificial neural networks trained with simulated data are shown to correctly and quickly determine film parameters from experimental X‐ray reflectivity curves.