Machine learning analysis for RHEED images using EM algorithm
-
- Yoshinari Asako
- Graduate School of Advanced Engineering, Tokyo University of Science National Institute for Materials Science
-
- Ando Yasunobu
- National Institute of Advanced Industrial Science and Technology
-
- Matsumura Tarojiro
- National Institute of Advanced Industrial Science and Technology
-
- Kotsugi Masato
- Graduate School of Advanced Engineering, Tokyo University of Science
-
- Nagamura Naoka
- Graduate School of Advanced Engineering, Tokyo University of Science National Institute for Materials Science Japan Science and Technology Agency PRESTO
Bibliographic Information
- Other Title
-
- EMアルゴリズムを用いたRHEED画像の機械学習自動解析
Abstract
<p>RHEED (reflection high-energy electron diffraction) is a widely used method for in-situ surface structural analysis of thin films. Since it is difficult to interpret the entire patterns quantitatively, researchers often use limited information such as the intensity oscillation at a given diffraction spot in film thickness estimation. Here, we adopted machine learning techniques for feature extraction from the entire RHEED patterns. We performed peak fitting analysis of the luminance histogram obtained from the time-series image datasets of RHEED patterns of Si surface superstructures during Indium deposition using EM algorithm. One peak component corresponds to the background, and the other corresponds to the diffraction spots. By tracking the change in the dispersion value of the peak, the optimal time for preparing each surface superstructure could be estimated automatically. Our method is expected for the application in data-driven material synthesis.</p>
Journal
-
- Abstract book of Annual Meeting of the Japan Society of Vacuum and Surface Science
-
Abstract book of Annual Meeting of the Japan Society of Vacuum and Surface Science 2021 (0), 2Dp03S-, 2021
The Japan Society of Vacuum and Surface Science
- Tweet
Details 詳細情報について
-
- CRID
- 1390571968054430080
-
- NII Article ID
- 130008134164
-
- ISSN
- 24348589
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- CiNii Articles
-
- Abstract License Flag
- Disallowed