Automatically Extracting Surface-Wave Group and Phase Velocity Dispersion Curves from Dispersion Spectrograms Using a Convolutional Neural Network

Yang, Shaobo1; Zhang, Haijiang1,2; Gu, Ning1,3; Gao, Ji1,2; Xu, Jian1; Jin, Jiaqi1; Li, Junlun1,2; Yao, Huajian1,2

2022-05-01

10.1785/0220210280

SEISMOLOGICAL RESEARCH LETTERS   影响因子和分区

0895-0695

1938-2057

To image high-resolution crustal and upper-mantle structures, ambient noise tomography (ANT) has been widely used on local and regional dense seismic arrays. One of the key steps in ANT is to extract surface-wave group and phase velocity dispersion curves from cross-correlation functions of continuous ambient noise recordings. One traditional way is to manually pick the dispersion curves from dispersion spectrograms in the period-velocity domains, which is very labor intensive and time consuming. Another way is to automatically pick the dispersion curves using some predefined criteria, which are not reliable in many cases especially for phase velocity data. In this study, we propose a novel method named DisperPicker to automatically extract fundamental mode group and phase velocity dispersion curves using a convolutional neural network (CNN). The inputs to CNN include paired group and phase velocity dispersion spectrograms in the period-velocity domains, which are calculated from empirical surface-wave Green's functions. In this way, group velocity dispersion curves can implicitly guide the extraction of phase velocity dispersion curves, which have large ambiguities to pick on the dispersion spectrograms. The labels or outputs of the network are the probability images converted from dispersion curves. The U-net architecture is adopted because it is powerful for image processing. We have assembled short-period surfacewave data from three different dense seismic arrays to train the network. The trained network is further tested and validated by two datasets close to Chao Lake, China. The tests show that DisperPicker has the generalization ability to efficiently and accurately extract dispersion curves of large datasets without new training.

SCI ; EI

英语

其他

National Key R&D Program of China[2018YFC1504102] ; National Natural Science Foundation of China[41961134001]

Geochemistry & Geophysics

Geochemistry & Geophysics

WOS:000792403700003

SEISMOLOGICAL SOC AMER

20222012120906

Acoustic noise ; Convolution ; Image processing ; Large dataset ; Phase velocity ; Seismology ; Spectrographs

Earthquake Measurements and Analysis:484.1 ; Electromagnetic Waves in Different Media:711.1 ; Information Theory and Signal Processing:716.1 ; Data Processing and Image Processing:723.2 ; Optical Devices and Systems:741.3 ; Acoustic Noise:751.4

GEOSCIENCES

Web of Science

1.Univ Sci & Technol China, Sch Earth & Space Sci, Lab Seismol & Phys Earths Interior, Hefei, Anhui, Peoples R China
2.Univ Sci & Technol China, Mengcheng Natl Geophys Observ, Hefei, Anhui, Peoples R China
3.Southern Univ Sci & Technol, Dept Earth & Space Sci, Shenzhen, Peoples R China

Yang, Shaobo,Zhang, Haijiang,Gu, Ning,et al. Automatically Extracting Surface-Wave Group and Phase Velocity Dispersion Curves from Dispersion Spectrograms Using a Convolutional Neural Network[J]. SEISMOLOGICAL RESEARCH LETTERS,2022,93(3):1549-1563.

Yang, Shaobo.,Zhang, Haijiang.,Gu, Ning.,Gao, Ji.,Xu, Jian.,...&Yao, Huajian.(2022).Automatically Extracting Surface-Wave Group and Phase Velocity Dispersion Curves from Dispersion Spectrograms Using a Convolutional Neural Network.SEISMOLOGICAL RESEARCH LETTERS,93(3),1549-1563.

Yang, Shaobo,et al."Automatically Extracting Surface-Wave Group and Phase Velocity Dispersion Curves from Dispersion Spectrograms Using a Convolutional Neural Network".SEISMOLOGICAL RESEARCH LETTERS 93.3(2022):1549-1563.