Toward fully automated UED operation using two-stage machine learning model

doi:10.1038/s41598-022-08260-7

	Toward fully automated UED operation using two-stage machine learning model
	Zhang, Zhe 1; Yang, Xi 2; Huang, Xiaobiao 1; Shaftan, Timur 2; Smaluk, Victor 2; Song, Minghao 1; Wan, Weishi3 ; Wu, Lijun 4; Zhu, Yimei 4
	2022-03-10
发表期刊	SCIENTIFIC REPORTS (IF:3.8[JCR-2023],4.3[5-Year])
ISSN	2045-2322
EISSN	2045-2322
卷号	12 期号:1
发表状态	已发表
DOI	10.1038/s41598-022-08260-7
摘要	To demonstrate the feasibility of automating UED operation and diagnosing the machine performance in real time, a two-stage machine learning (ML) model based on self-consistent start-to-end simulations has been implemented. This model will not only provide the machine parameters with adequate precision, toward the full automation of the UED instrument, but also make real-time electron beam information available as single-shot nondestructive diagnostics. Furthermore, based on a deep understanding of the root connection between the electron beam properties and the features of Bragg-diffraction patterns, we have applied the hidden symmetry as model constraints, successfully improving the accuracy of energy spread prediction by a factor of five and making the beam divergence prediction two times faster. The capability enabled by the global optimization via ML provides us with better opportunities for discoveries using near-parallel, bright, and ultrafast electron beams for single-shot imaging. It also enables directly visualizing the dynamics of defects and nanostructured materials, which is impossible using present electron-beam technologies.
URL	查看原文
收录类别	SCIE ; SCI
语种	英语
资助项目	U.S. Department of Energy["DE-AC02-76SF00515","DE-SC0012704"] ; Brookhaven National Laboratory Directed Research and Development Program["16-010","19-016","22-029"] ; National Energy Research Scientific Computing Center (NERSC), a U.S. Department of Energy Office of Science User Facility located at Lawrence Berkeley National Laboratory[DE-AC02-05CH11231]
WOS研究方向	Science & Technology - Other Topics
WOS类目	Multidisciplinary Sciences
WOS记录号	WOS:000838209800024
出版者	NATURE PORTFOLIO
Scopus 记录号	2-s2.0-85126222669
来源库	Scopus
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/165037
专题	物质科学与技术学院_外聘教师
通讯作者	Yang, Xi
作者单位	1.SLAC Natl Accelerator Lab, Menlo Pk, CA 94025 USA 2.Brookhaven Natl Lab, Natl Synchrotron Light Source II, Upton, NY 11973 USA 3.ShanghaiTech Univ, Sch Phys Sci & Technol, Shanghai 201210, Peoples R China 4.Brookhaven Natl Lab, Condensed Matter Phys & Mat Sci Div, Upton, NY 11973 USA
推荐引用方式 GB/T 7714	Zhang, Zhe,Yang, Xi,Huang, Xiaobiao,et al. Toward fully automated UED operation using two-stage machine learning model[J]. SCIENTIFIC REPORTS,2022,12(1).
APA	Zhang, Zhe.,Yang, Xi.,Huang, Xiaobiao.,Shaftan, Timur.,Smaluk, Victor.,...&Zhu, Yimei.(2022).Toward fully automated UED operation using two-stage machine learning model.SCIENTIFIC REPORTS,12(1).
MLA	Zhang, Zhe,et al."Toward fully automated UED operation using two-stage machine learning model".SCIENTIFIC REPORTS 12.1(2022).