干旱区生态环境知识资源中心(Arid): Desert Seismic Low-Frequency Noise Attenuation Using Low-Rank Decomposition-Based Denoising Convolutional Neural Network

Arid

DOI	10.1109/TGRS.2021.3055506
	Desert Seismic Low-Frequency Noise Attenuation Using Low-Rank Decomposition-Based Denoising Convolutional Neural Network
	Ma, Haitao; Wang, Yuzhuo; Li, Yue; Zhao, Yuxing
通讯作者	Li, Y (corresponding author), Jilin Univ, Dept Informat, Coll Commun Engn, Changchun 130012, Peoples R China.
来源期刊	IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
ISSN	0196-2892
EISSN	1558-0644
出版年	2022
卷号	60
英文摘要	Desert seismic data are often characterized by low signal-to-noise ratio (SNR) due to the fickle surface conditions and desert random noise with nonstationarity, nonlinearity, spatial directivity, and low-frequency characteristics. This low SNR is likely to affect the following inversion and interpretation. Therefore, robust noise attenuation is crucial to improve the SNR of desert seismic data. We propose a novel method alternating direction method of multipliers-based denoising convolutional neural network (ADMM-CNN) by combining low-rank decomposition with feed-forward denoising convolutional neural network (DnCNN). DnCNN is a deep-learning-based method for noise removal, which can make good noise attenuation performance through training. However, there is no feature extraction procedure before model learning in its structure, so DnCNN cannot make full use of the prior information of signals. Combining low-rank decomposition just addresses this issue. Compared with DnCNN, our method has two main novelties. First, we use the synthetic seismic data that resemble the characteristics of field desert seismic data and desert noise to train the ADMM-CNN. Second, we use ADMM to decompose the data into three layers (low-rank, sparse, and perturbation) which are used as the inputs of three channels neural network. Through this decomposition, the neural network can capture more features and prior information of desert seismic data. Both synthetic field data tests demonstrate the robuster performance of ADMM-CNN compared to traditional methods and DnCNN, also that the ADMM-CNN method suppresses the desert noise more thoroughly and greatly improves SNR of desert seismic data at the same time.
英文关键词	Convolution Attenuation Neural networks Training Signal to noise ratio Noise reduction Noise measurement Convolutional neural network (CNN) deep learning desert seismic noise attenuation low-rank decomposition
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000726094900106
WOS关键词	BACKGROUND-NOISE ; RECONSTRUCTION ; ALGORITHM
WOS类目	Geochemistry & Geophysics ; Engineering, Electrical & Electronic ; Remote Sensing ; Imaging Science & Photographic Technology
WOS研究方向	Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/374400
作者单位	[Ma, Haitao; Wang, Yuzhuo; Li, Yue; Zhao, Yuxing] Jilin Univ, Dept Informat, Coll Commun Engn, Changchun 130012, Peoples R China
推荐引用方式 GB/T 7714	Ma, Haitao,Wang, Yuzhuo,Li, Yue,et al. Desert Seismic Low-Frequency Noise Attenuation Using Low-Rank Decomposition-Based Denoising Convolutional Neural Network[J],2022,60.
APA	Ma, Haitao,Wang, Yuzhuo,Li, Yue,&Zhao, Yuxing.(2022).Desert Seismic Low-Frequency Noise Attenuation Using Low-Rank Decomposition-Based Denoising Convolutional Neural Network.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,60.
MLA	Ma, Haitao,et al."Desert Seismic Low-Frequency Noise Attenuation Using Low-Rank Decomposition-Based Denoising Convolutional Neural Network".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 60(2022).