南方科技大学知识苑(SUSTech KC): Convolutional Neural Network, Res-Unet++, -Based Dispersion Curve Picking From Noise Cross-Correlations

题名	Convolutional Neural Network, Res-Unet++, -Based Dispersion Curve Picking From Noise Cross-Correlations
作者	Song，Weibin1,2,3 ; Feng，Xuping2 ; Wu，Gaoxiong 4; Zhang，Gongheng2 ; Liu，Ying 5; Chen，Xiaofei1,2,3
通讯作者	Chen，Xiaofei
发表日期	2021-11-01
DOI	10.1029/2021JB022027
发表期刊	JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH 影响因子和分区
ISSN	2169-9313
EISSN	2169-9356
卷号	126 期号:11
摘要	Ambient seismic noise cross-correlation has been widely applied in surface wave tomography at regional to global scales, including for seismic exploration of near-surface structures. Reliable seismic imaging requires the accurate selection of dispersion curves. However, manual picking has become cumbersome work with the increase in available correlation traces; it is even more difficult when the number of dispersion curves increases by using frequency-Bessel (F-J) transform. Here, we show that the neural network Res-Unet++ can automatically and accurately extract both fundamental dispersion curves and overtones from the F-J dispersion spectra after training the network. Results show that selected dispersion curves had high accuracies in the synthetic data (greater than 95%). The network could effectively extract both the fundamental and higher modes in real data, and transfer learning improved the adaptability of neural networks for different geological areas. The obtained dispersion curves from the real data agreed well with those acquired manually and were advantageous for generating more effective dispersion points.
关键词	ambient seismic noise deep learning dispersion curves neural network surface wave transfer learning
相关链接	[Scopus记录]
收录类别	SCI
语种	英语
学校署名	第一 ; 通讯
资助项目	Shenzhen Key Laboratory of Deep Offshore Oil and Gas Exploration Technology[ZDSYS20190902093007855] ; Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)[GML2019ZD0203] ; Shenzhen Science and Technology Program[KQTD20170810111725321] ; National Natural Science Foundation of China["U1901602",41790465] ; leading talents of Guangdong province program[2016LJ06N652]
WOS研究方向	Geochemistry & Geophysics
WOS类目	Geochemistry & Geophysics
WOS记录号	WOS:000723102600032
出版者	AMER GEOPHYSICAL UNION
ESI学科分类	GEOSCIENCES
Scopus记录号	2-s2.0-85119834040
来源库	Scopus
引用统计	被引频次[WOS]：11
成果类型	期刊论文
条目标识符	http://sustech.caswiz.com/handle/2SGJ60CL/258156
专题	理学院_地球与空间科学系
作者单位	1.Shenzhen Key Laboratory of Deep Offshore Oil and Gas Exploration Technology,Southern University of Science and Technology,Shenzhen,China 2.Department of the Earth and Space Sciences,Southern University of Science and Technology,Shenzhen,China 3.Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou),Guangzhou,China 4.School of the Earth and Space Sciences,University of Sciences and Technology of China,Hefei,China 5.Center of AI and Intelligent Operation,China Mobile Communications Research Institute,Beijing,China
第一作者单位	南方科技大学; 地球与空间科学系
通讯作者单位	南方科技大学; 地球与空间科学系
第一作者的第一单位	南方科技大学
推荐引用方式 GB/T 7714	Song，Weibin,Feng，Xuping,Wu，Gaoxiong,et al. Convolutional Neural Network, Res-Unet++, -Based Dispersion Curve Picking From Noise Cross-Correlations[J]. JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH,2021,126(11).
APA	Song，Weibin,Feng，Xuping,Wu，Gaoxiong,Zhang，Gongheng,Liu，Ying,&Chen，Xiaofei.(2021).Convolutional Neural Network, Res-Unet++, -Based Dispersion Curve Picking From Noise Cross-Correlations.JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH,126(11).
MLA	Song，Weibin,et al."Convolutional Neural Network, Res-Unet++, -Based Dispersion Curve Picking From Noise Cross-Correlations".JOURNAL OF GEOPHYSICAL RESEARCH-SOLID EARTH 126.11(2021).