Applying Feature Transformation-Based Domain Confusion to Neural Network for the Denoising of Dispersion Spectrograms

Song, Weibin3; Yuan, Shichuan2; Cheng, Ming2; Wang, Guanchao4; Li, Yilong2; Chen, Xiaofei1,2,3

2024

10.1785/0220230103

SEISMOLOGICAL RESEARCH LETTERS   影响因子和分区

0895-0695

1938-2057

Ambient noise tomography has been widely used to estimate the shear-wave velocity structure of the Earth. A key step in this method is to pick dispersions from dispersion spectrograms. Using the frequency-Bessel (F-J) transform, the generated spectrograms can provide more dispersion information by including higher modes in addition to the fundamental mode. With the increasing availability of these spectrograms, manually picking dispersion curves is highly time and energy consuming. Consequently, neural networks have been used for automatically picking dispersions. Dispersion curves are picked based on deep learning mainly for denoising these spectrograms. In several studies, the neural network was solely trained, and its performance was verified for the denoising. However, they all learn single-source data in the training of neural network. It will lead the regionality of trained neural network. Even if we can use domain adaptation to improve its performance and achieve some success, there are still some spectrograms that cannot be solved effectively. Therefore, multisources training is useful and could reduce the regionality in training stage. Normally, dispersion spectrograms from multisources have feature differences of dispersion curves, especially for higher modes in F-J spectrograms. Thus, we propose a training strategy based on domain confusion through which the neural network effectively learns spectrograms from multisources. After domain confusion, the trained neural network can effectively process large number of test data and help us easily obtain more dispersion curves automatically. The proposed study can provide a deep insight into the denoising of dispersion spectrograms by neural network and facilitate ambient noise tomography.

SCI ; EI

英语

第一 ; 通讯

Guangdong Provincial Key Laboratory of Geophysical High -resolution Imaging Technology[2022B1212010002] ; National Natural Science Foundation of China["U1901602","41790465"] ; Shenzhen Science and Technology Program[KQTD20170810111725321] ; Shenzhen Key Laboratory of Deep Offshore Oil and Gas Exploration Technology[ZDSYS20190902093007855] ; Leading talents of the Guangdong province program[2016LJ06N652]

Geochemistry & Geophysics

Geochemistry & Geophysics

WOS:001198646900002

SEISMOLOGICAL SOC AMER

GEOSCIENCES

Web of Science

1.Southern Univ Sci & Technol, Shenzhen Key Lab Deep Offshore Oil & Gas Explorat, Shenzhen, Guangdong, Peoples R China
2.Southern Univ Sci & Technol, Dept Earth & Space Sci, Shenzhen, Guangdong, Peoples R China
3.Southern Univ Sci & Technol, Guangdong Prov Key Lab Geophys High Resolut Imagin, Shenzhen, Peoples R China
4.Natl Engn Res Ctr Digital Construct & Evaluat Urba, China Railway Design Corp, Tianjin, Peoples R China

Song, Weibin,Yuan, Shichuan,Cheng, Ming,et al. Applying Feature Transformation-Based Domain Confusion to Neural Network for the Denoising of Dispersion Spectrograms[J]. SEISMOLOGICAL RESEARCH LETTERS,2024,95(1).

Song, Weibin,Yuan, Shichuan,Cheng, Ming,Wang, Guanchao,Li, Yilong,&Chen, Xiaofei.(2024).Applying Feature Transformation-Based Domain Confusion to Neural Network for the Denoising of Dispersion Spectrograms.SEISMOLOGICAL RESEARCH LETTERS,95(1).

Song, Weibin,et al."Applying Feature Transformation-Based Domain Confusion to Neural Network for the Denoising of Dispersion Spectrograms".SEISMOLOGICAL RESEARCH LETTERS 95.1(2024).