Classification of in situ reflection high energy electron diffraction images by principal component analysis

Abstract The reflection high-energy electron diffraction (RHEED) method is widely used for the in situ observation of molecular beam epitaxy (MBE). This because RHEED pattern dynamically changes according to growth conditions, such as surface temperature and material supply. However, date, has been categorized recognized based on experience researcher. In this study, we investigated classification datasets without using labeling by principal component analysis that reduces dimensionality data. images were successfully classified during MBE GaAs, demonstrating unsupervised learning can be recognize patterns.