Machine-learning-assisted analysis of transition metal dichalcogenide thin-film growth
Abstract In situ reflective high-energy electron diffraction (RHEED) is widely used to monitor the surface crystalline state during thin-film growth by molecular beam epitaxy (MBE) and pulsed laser deposition. With the recent development of machine learning (ML), ML-assisted analysis of RHEED videos...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-02-01
|
| Series: | Nano Convergence |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40580-023-00359-5 |
| _version_ | 1797863848554790912 |
|---|---|
| author | Hyuk Jin Kim Minsu Chong Tae Gyu Rhee Yeong Gwang Khim Min-Hyoung Jung Young-Min Kim Hu Young Jeong Byoung Ki Choi Young Jun Chang |
| author_facet | Hyuk Jin Kim Minsu Chong Tae Gyu Rhee Yeong Gwang Khim Min-Hyoung Jung Young-Min Kim Hu Young Jeong Byoung Ki Choi Young Jun Chang |
| author_sort | Hyuk Jin Kim |
| collection | DOAJ |
| description | Abstract In situ reflective high-energy electron diffraction (RHEED) is widely used to monitor the surface crystalline state during thin-film growth by molecular beam epitaxy (MBE) and pulsed laser deposition. With the recent development of machine learning (ML), ML-assisted analysis of RHEED videos aids in interpreting the complete RHEED data of oxide thin films. The quantitative analysis of RHEED data allows us to characterize and categorize the growth modes step by step, and extract hidden knowledge of the epitaxial film growth process. In this study, we employed the ML-assisted RHEED analysis method to investigate the growth of 2D thin films of transition metal dichalcogenides (ReSe2) on graphene substrates by MBE. Principal component analysis (PCA) and K-means clustering were used to separate statistically important patterns and visualize the trend of pattern evolution without any notable loss of information. Using the modified PCA, we could monitor the diffraction intensity of solely the ReSe2 layers by filtering out the substrate contribution. These findings demonstrate that ML analysis can be successfully employed to examine and understand the film-growth dynamics of 2D materials. Further, the ML-based method can pave the way for the development of advanced real-time monitoring and autonomous material synthesis techniques. Graphical Abstract |
| first_indexed | 2024-04-09T22:42:13Z |
| format | Article |
| id | doaj.art-0a52db1997a54afe9cfa88f83f03424b |
| institution | Directory Open Access Journal |
| issn | 2196-5404 |
| language | English |
| last_indexed | 2024-04-09T22:42:13Z |
| publishDate | 2023-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Nano Convergence |
| spelling | doaj.art-0a52db1997a54afe9cfa88f83f03424b2023-03-22T12:02:54ZengSpringerOpenNano Convergence2196-54042023-02-0110111010.1186/s40580-023-00359-5Machine-learning-assisted analysis of transition metal dichalcogenide thin-film growthHyuk Jin Kim0Minsu Chong1Tae Gyu Rhee2Yeong Gwang Khim3Min-Hyoung Jung4Young-Min Kim5Hu Young Jeong6Byoung Ki Choi7Young Jun Chang8Department of Physics, University of SeoulDepartment of Physics, University of SeoulDepartment of Physics, University of SeoulDepartment of Physics, University of SeoulDepartment of Energy Science, Sungkyunkwan University (SKKU)Department of Energy Science, Sungkyunkwan University (SKKU)Graduate School of Semiconductor Materials and Devices Engineering, Ulsan National Institute of Science and Technology (UNIST)Department of Physics, University of SeoulDepartment of Physics, University of SeoulAbstract In situ reflective high-energy electron diffraction (RHEED) is widely used to monitor the surface crystalline state during thin-film growth by molecular beam epitaxy (MBE) and pulsed laser deposition. With the recent development of machine learning (ML), ML-assisted analysis of RHEED videos aids in interpreting the complete RHEED data of oxide thin films. The quantitative analysis of RHEED data allows us to characterize and categorize the growth modes step by step, and extract hidden knowledge of the epitaxial film growth process. In this study, we employed the ML-assisted RHEED analysis method to investigate the growth of 2D thin films of transition metal dichalcogenides (ReSe2) on graphene substrates by MBE. Principal component analysis (PCA) and K-means clustering were used to separate statistically important patterns and visualize the trend of pattern evolution without any notable loss of information. Using the modified PCA, we could monitor the diffraction intensity of solely the ReSe2 layers by filtering out the substrate contribution. These findings demonstrate that ML analysis can be successfully employed to examine and understand the film-growth dynamics of 2D materials. Further, the ML-based method can pave the way for the development of advanced real-time monitoring and autonomous material synthesis techniques. Graphical Abstracthttps://doi.org/10.1186/s40580-023-00359-5Machine learningRHEEDPrincipal component analysisK-means clusteringTMDCReSe2 |
| spellingShingle | Hyuk Jin Kim Minsu Chong Tae Gyu Rhee Yeong Gwang Khim Min-Hyoung Jung Young-Min Kim Hu Young Jeong Byoung Ki Choi Young Jun Chang Machine-learning-assisted analysis of transition metal dichalcogenide thin-film growth Nano Convergence Machine learning RHEED Principal component analysis K-means clustering TMDC ReSe2 |
| title | Machine-learning-assisted analysis of transition metal dichalcogenide thin-film growth |
| title_full | Machine-learning-assisted analysis of transition metal dichalcogenide thin-film growth |
| title_fullStr | Machine-learning-assisted analysis of transition metal dichalcogenide thin-film growth |
| title_full_unstemmed | Machine-learning-assisted analysis of transition metal dichalcogenide thin-film growth |
| title_short | Machine-learning-assisted analysis of transition metal dichalcogenide thin-film growth |
| title_sort | machine learning assisted analysis of transition metal dichalcogenide thin film growth |
| topic | Machine learning RHEED Principal component analysis K-means clustering TMDC ReSe2 |
| url | https://doi.org/10.1186/s40580-023-00359-5 |
| work_keys_str_mv | AT hyukjinkim machinelearningassistedanalysisoftransitionmetaldichalcogenidethinfilmgrowth AT minsuchong machinelearningassistedanalysisoftransitionmetaldichalcogenidethinfilmgrowth AT taegyurhee machinelearningassistedanalysisoftransitionmetaldichalcogenidethinfilmgrowth AT yeonggwangkhim machinelearningassistedanalysisoftransitionmetaldichalcogenidethinfilmgrowth AT minhyoungjung machinelearningassistedanalysisoftransitionmetaldichalcogenidethinfilmgrowth AT youngminkim machinelearningassistedanalysisoftransitionmetaldichalcogenidethinfilmgrowth AT huyoungjeong machinelearningassistedanalysisoftransitionmetaldichalcogenidethinfilmgrowth AT byoungkichoi machinelearningassistedanalysisoftransitionmetaldichalcogenidethinfilmgrowth AT youngjunchang machinelearningassistedanalysisoftransitionmetaldichalcogenidethinfilmgrowth |