Transverse Velocity Field Measurement of Solar High-resolution Images Based on Unsupervised Deep Learning

doi:10.1088/1674-4527/adbc38

YNAO OpenIR > 其他

	Transverse Velocity Field Measurement of Solar High-resolution Images Based on Unsupervised Deep Learning
	Shang, Zhen-Hong 1,2; Chen, Long 1; Qiang, Zhen-Ping 3; Bi Y(毕以)4 ; Li, Run-Xin 1,2
发表期刊	RESEARCH IN ASTRONOMY AND ASTROPHYSICS
	2025-03-01
卷号	25 期号:3
DOI	10.1088/1674-4527/adbc38
产权排序	第4完成单位
收录类别	SCI
关键词	methods: data analysis techniques: image processing Sun: fundamental parameters
摘要	Measuring the transverse velocity field in high-resolution solar images is essential for understanding solar dynamics. This paper introduces an innovative unsupervised deep learning optical flow model designed to calculate the transverse velocity field, addressing the challenges of missing optical flow labels and the limited accuracy of velocity field measurements in high-resolution solar images. The proposed method converts the transverse velocity field computation problem into an optical flow computation problem, using two forward propagations of features to get rid of the reliance on optical flow labels. Additionally, it reduces the impact of the Brightness Consistency constraint on optical flow accuracy by identifying and handling optical flow outliers. We apply this method to compute the transverse velocity fields of high-resolution solar image sequences from the H alpha and TiO bands, observed by the New Vacuum Solar Telescope. Comparative experiments with several well-established optical flow methods, including those based on supervised deep learning models, show that our approach outperforms the comparison methods according to key evaluation metrics such as Residual Map Mean, Residual Map Variance, Cross Correlation, and Structural Similarity Index Measure. Moreover, since optical flow captures the fundamental motion information in image sequences, the proposed method can be applied to a variety of research areas, including solar image registration, sequence alignment, image super-resolution, magnetic field calibration, and solar activity forecasting. The code is available at https://github.com/jackie-willianm/Transverse-Velocity-Field-Measurement-of-Solar-High-Resolution-Images.
资助项目	National Natural Science Foundation of China (NSFC)[12063002]; National Natural Science Foundation of China (NSFC)[12163004]
项目资助者	National Natural Science Foundation of China (NSFC)[12063002, 12163004]
语种	英语
学科领域	天文学 ; 太阳与太阳系
文章类型	Article
出版者	IOP Publishing Ltd
出版地	TEMPLE CIRCUS, TEMPLE WAY, BRISTOL BS1 6BE, ENGLAND
ISSN	1674-4527
URL	查看原文
WOS记录号	WOS:001451116500001
WOS研究方向	Astronomy & Astrophysics
WOS类目	Astronomy & Astrophysics
关键词[WOS]	OPTICAL-FLOW
引用统计
文献类型	期刊论文
版本	出版稿
条目标识符	http://ir.ynao.ac.cn/handle/114a53/28234
专题	其他
作者单位	1.Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China; 2.Yunnan Key Laboratory of Artificial Intelligence, Kunming University of Science and Technology, Kunming 650500, China; 3.College of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming 650224, China; 4.Yunnan Observatories, Chinese Academy of Sciences, Kunming 650216, China
推荐引用方式 GB/T 7714	Shang, Zhen-Hong,Chen, Long,Qiang, Zhen-Ping,et al. Transverse Velocity Field Measurement of Solar High-resolution Images Based on Unsupervised Deep Learning[J]. RESEARCH IN ASTRONOMY AND ASTROPHYSICS,2025,25(3).
APA	Shang, Zhen-Hong,Chen, Long,Qiang, Zhen-Ping,毕以,&Li, Run-Xin.(2025).Transverse Velocity Field Measurement of Solar High-resolution Images Based on Unsupervised Deep Learning.RESEARCH IN ASTRONOMY AND ASTROPHYSICS,25(3).
MLA	Shang, Zhen-Hong,et al."Transverse Velocity Field Measurement of Solar High-resolution Images Based on Unsupervised Deep Learning".RESEARCH IN ASTRONOMY AND ASTROPHYSICS 25.3(2025).

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Transverse Velocity （1220KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览请求全文