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

FM: Fachverband Funktionsmaterialien

FM 11: Poster Session Functional Materials

FM 11.3: Poster

Dienstag, 10. März 2026, 18:00–20:30, P4

Epitaxial Growth and Optimization of LiNbO3 Thin Films on LiTaO3 and Al2O3 by Pulsed Laser Deposition Using Machine Learning — •Hyeyeon Cho, Milena Petkovic, Steffen Ganshow, and Jutta Schwarzkopf — Leibniz-Institut für Kristallzüchtung, Max-Born-Straße 2, 12489 Berlin, Germany

Lithium niobate (LiNbO3) thin films are widely used in electro-optical and electro-acoustic devices due to their excellent ferroelectric, piezoelectric, and nonlinear optical properties, offering broader bandwidths at higher frequencies and reduced operational voltages compared to bulk materials. The development of high-quality, phase-pure, and smooth LiNbO3 films is essential for achieving superior device performance. Pulsed Laser Deposition (PLD) offers precise control over growth parameters, enabling the fabrication of epitaxial LiNbO3 layers with tunable structural properties. In our work, we investigated the epitaxial growth of LiNbO3 thin films on LiTaO3 and Al2O3 substrates using PLD. The influence of various PLD growth conditions and substrate materials was systematically investigated with regard to phase formation and structural ordering by x-ray diffraction and surface roughness by atomic force microscopy. Furthermore, a four-step machine learning workflow, including Artificial Neural Network (ANN) and Random Forest (RF) models, was employed to analyze the nonlinear relationships between PLD parameters and structural film properties. This combined experimental and computational approach accelerates development and provides deeper insight into LiNbO3 thin film growth for advanced photonic and optoelectronic applications.

Keywords: LiNbO3 thin films; Pulsed Laser Deposition; Machine Learning; Artificial Neural Network; Random Forest