[9p-Z01-1~18] 15.3 III-V-group epitaxial crystals, Fundamentals of epitaxy

[9p-Z01-16] Classification of RHEED patterns using principal component analysis

〇JINKWAN KWOEN¹, Yasuhiko Arakawa¹ (1.Univ.Tokyo NanoQuine)

Keywords:RHEED, Principal Component Analysis, Machine Learning

In the principal component analysis, the correlation can be clustered according to the principal component of each data, and each can be classified. There is also a feature that is "unsupervised learning" that can summarize the features of data without the need for prior information such as labels. Here, we report that we collected reflection high energy electron diffraction (RHEED) images from MBE growth of GaAs on GaAs substrates and succeeded in classifying the patterns by principal component analysis.