Predicting Synthesis–Structure Relationships in Epitaxially–Grown Semiconductors with Quantum and Classical Supervised Learning

In this work, data detailing hundreds of plasma–assisted molecular beam epitaxy (PAMBE) thin film material growth experiments each of ZnO and various nitride semiconductors have been organized into separate, composition–specific data sets. For each experiment, the complete set of PAMBE growth parameters are associated with binary measures of crystallinity (1 for monocrystalline, 0 for polycrystalline) and surface morphology (1 for atomically–flat, 0 for uneven) as determined by reflection high–energy electron diffraction (RHEED) patterns. Additionally, a Brag–Williams measure of lattice disorder (S²) is included as an additional figure of merit for investigation. Quantum as well as conventional supervised learning algorithms – including logistic regression, tree–based algorithms, and quantum support vector machines – are trained on the data to study which growth parameters are most statistically important for influencing crystallinity, surface morphology, and S². The probabilities of obtaining monocrystalline and atomically flat thin film crystals are predicted across processing spaces of the two most statistically significant synthesis parameters. S² is also predicted across the same growth spaces. The predictions indicate that different growth conditions are of interest depending on whether a single crystalline sample, a flat surface, or a well–ordered lattice is desired.