干旱区生态环境知识资源中心(Arid): Parameter-shared variational auto-encoding adversarial network for desert seismic data denoising in Northwest China

Arid

DOI	10.1016/j.jappgeo.2021.104428
	Parameter-shared variational auto-encoding adversarial network for desert seismic data denoising in Northwest China
	Li, Yue; Wang, Cong; Tian, Yanan; Wang, Shengnan
通讯作者	Tian, YA (corresponding author), Jilin Univ, Coll Commun Engn, Dept Informat, Changchun 130012, Peoples R China.
来源期刊	JOURNAL OF APPLIED GEOPHYSICS
ISSN	0926-9851
EISSN	1879-1859
出版年	2021
卷号	193
英文摘要	One of the key and difficult points in seismic data processing is seismic data denoising. Under the influence of the acquisition environment, the collected seismic data usually have low signal-to-noise ratio (SNR) and low resolution. In desert region of western China, different from other regions, the random noise there has complex characteristics of non-Gaussian, non-stationary and non-linearity. Its main frequency is quite low and its spectral overlap with those of effective signals. Moreover, large amount of data and intelligent requirements make traditional denoising methods encounter difficulties. In addition, the existing deep learning denoising methods also reveal two problems: first, they can only effectively suppress simple seismic noise such as Gaussian noise. But for the case of desert noise, they usually mistakenly judge noise as effective signals and destroy signal characteristic structure. Second, what is more important, in supervised-based methods paired noisy and pure data are usually used as training set. However, there is no noise-free data in actual desert seismic data, which severely limits the processing performance of supervised-based networks. Thus, a new parameter-shared variational auto-encoding adversarial network (PS-VAAN) is proposed for desert seismic data denoising in this paper. This new method includes two encoders, two generators and two discriminators. It can realize domain conversion from noisy data domain to pure data domain. We construct relatively complete unpaired pure and noisy data training sets for training, and design reconstruction loss function and adversarial loss function to optimize network parameters. Moreover, cycle-consistency loss is introduced to make sure two domains mapping into the same space. Compared with the state-of-art denoising methods on synthetic and actual seismic records, the proposed method not only has superior denoising ability, but also has strong feature extraction and fitting ability to recover effective signals with almost no energy loss.
英文关键词	Desert seismic data Noise suppression Unpaired training Parameter shared
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000691323300016
WOS关键词	NOISE ATTENUATION
WOS类目	Geosciences, Multidisciplinary ; Mining & Mineral Processing
WOS研究方向	Geology ; Mining & Mineral Processing
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/363729
作者单位	[Li, Yue; Wang, Cong; Tian, Yanan; Wang, Shengnan] Jilin Univ, Coll Commun Engn, Dept Informat, Changchun 130012, Peoples R China
推荐引用方式 GB/T 7714	Li, Yue,Wang, Cong,Tian, Yanan,et al. Parameter-shared variational auto-encoding adversarial network for desert seismic data denoising in Northwest China[J],2021,193.
APA	Li, Yue,Wang, Cong,Tian, Yanan,&Wang, Shengnan.(2021).Parameter-shared variational auto-encoding adversarial network for desert seismic data denoising in Northwest China.JOURNAL OF APPLIED GEOPHYSICS,193.
MLA	Li, Yue,et al."Parameter-shared variational auto-encoding adversarial network for desert seismic data denoising in Northwest China".JOURNAL OF APPLIED GEOPHYSICS 193(2021).