Controlled thin film growth through machine-learning based closed-loop feedback with online X-ray scattering analysis

In recent years, X-ray scattering has received a significant boost due to the increased use of machine learning strategies in the analysis of data acquired at synchrotron sources. With this proposal we intend to leverage ML based real-time data analysis integrated into modern beamline environments and thereby provide low-barrier access to ML based techniques for many user groups visiting photon sources. As a proof-of-concept, we aim at growing organic molecular thin films of two distinct molecular components, monitor the growth with X-ray reflectivity and establish a closed loop between real-time, ML-based online data analysis and the sample environment to tailor the deposition process of organic thin films on molecular monolayer level. We propose to grow multilayers of the two organic molecules PTCDI-C8 (N,N′-dioctyl-3,4,9,10-perylene tetracarboxylic diimide) and the N-alkane (TTC, C44H90) which are known for their high degree of structural order and layer-by-layer growth modes.