Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Chinese Journal of Geophysics》 2019-01
Add to Favorite Get Latest Update

Random seismic noise attenuation based on data augmentation and CNN

WANG YuQing;LU WenKai;LIU JinLin;ZHANG Meng;MIAO YongKang;Institute for Artificial Intelligence,Tsinghua University;State Key Laboratory of Intelligent Technology and Systems,Tsinghua University;Tsinghua University Beijing National Research Center for Information Science and Technology;Department of Automation,Tsinghua University;Shengli Oilfield Geophysical Research Institute of Sinopec;  
Convolutional neural network(CNN)has been widely adopted in various research fields of computer science.Combining the process of feature extracting and classification,CNN greatly simplifies traditional data processing task.However,as a data-driven algorithm,the generalization ability of CNN is limited in the problem of seismic noise attenuation which lacks labeled data.Tosolve this problem,we propose a CNN training framework based on data generation and augmentation for seismic noise attenuation.When processing synthetic data,we add Gaussian noise with different variance levels to clean seismic data and further augment training datasets to increase the diversity of features.For real seismic data,the clean data and corresponding noise are hard to acquire,thus we propose a method to generate labeled datasets directly from unlabeled noisy seismic data.In the proposed method,we apply existing denoising method to obtain the estimated clean data and estimated noise from real seismic data.The estimated data retains similar texture characteristics with clean data and the estimated noise has similar probability distribution with real seismic noise.We compare our method with F-X deconvolution,BM3D and adaptive frequency domain filtering method.The experiment results demonstrate that our method can efficiently attenuate random noise while preserving signals.Finally,we adopt neural network visualization methods to our CNN model and the visualization results explain the texture patterns learned by each layer of our network to some extent.
【Fund】: 国家自然科学基金项目(41674116)资助
【CateGory Index】: P631.4
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
Chinese Journal Full-text Database 2 Hits
1 Peng Cai Chang Zhi Zhu Shijun Geophysical Prospecting Company,Sichuan-Changqing United Drilling & Exploration Engineering Company,CNPC,Chengdu 610213,China;Noise elimination method based on curvelet transform[J];石油物探;2008-05
2 LIU Xin, HE Zhen-hua, HUANG De-ji(College of Information Engineering, Chengdu University of Technology , Chengdu,610059,China);Seismic data denoising research based on wavelet Transform[J];油气地球物理;2006-04
Chinese Journal Full-text Database 8 Hits
1 Zhang Shuting;Zhang Hua;Zhang Luoyi;Yang Hui;Shanxi Provincial Coal Geological Exploration, Geophysical Prospecting, Surveying and Mapping Institute;Fundamental Science on Radioactive Geology and Exploration Technology Laboratory, East China Institute of Technology;;Study on Curvelet Transform Prestack Denoising Technology Based on Local Thresthold[J];中国煤炭地质;2015-11
2 YIN Chuan;DU Xiangdong;SHEN Ye;LI Shaopeng;WANG Jian;General Research Institute,CNOOC;;Random Noise Attenuation in Curvelet Domain——By Taking Poststack Seismic Data of Desert Area for Example[J];石油天然气学报;2014-10
3 GAO-Tie;HUAN Heng-fei;XU Ying-kui;YANG Jia-jia;Shenyang Center,China Geological Survey;;Application of Curvelet transform denoising in potential field data[J];世界地质;2014-03
4 Liu Chengming;Wang Deli;Wang Tong;Feng Fei;Cheng Hao;Meng Gege;College of Geo-Exploration Science and Technology,Jilin University;;Random seismic noise attenuation based on the Shearlet transform[J];石油学报;2014-04
5 Meng Gege;Wang Deli;Chen Xin;College of Geo-Exploration Science and Technology,Jilin University;;Study on seismic data denoising method based on 3D Curvelet transform[J];石油物探;2014-03
6 LIU Lei~1,LIU Zhen~2,ZHANG Jun-hua~(2*)(1.Research Institute of Geological Sciences,Shengli Oil field,Dongying 257015,China;2.School of Geoscience,China University of Petroleum,Qingdao 266555,China);Denoising and detecting seismic weak signal based on curvelet thresholding method[J];地球物理学进展;2011-04
7 Zhou Jiaxiong1,2 Wang Yu2 Guo Aihua2Sun Yuecheng2 Li Haipeng2(1.China University of Geosciences,Wuhan,430074;2.Zhanjiang Branch of CNOOC Ltd.,Guangdong,524057);A study on denoising poststack 3D seismic data by curvelet transform[J];中国海上油气;2010-01
8 ZHOU Yan-jiang1,PAN Yi-shan2(1.Science School,Liaoning University of Engineering & Technology,Fuxin 123000,China;2.Liaoning University of Engineering & Technology,Fuxin 123000,China);P and S Wave Identification of Rock-burst Wave Based on Wavelet Transform[J];煤矿开采;2007-06
【Secondary Citations】
Chinese Journal Full-text Database 10 Hits
1 WU Fang-ping,DI Hong-wei(Institute of Optoelectronic Engineering,Jinan University,Guangzhou 510632,China);A image denoising method between soft and hard thresholding based on Curvelet transform[J];光学技术;2007-05
2 Peng Cai,Southwest Petroleum University, Chengdu 610500, China Zhu Shgun, Sun Jianku, Tang Miao, Xia Ling and Huang Dongshan.;K-L transformation in wavelet conversion domain and the analysis of de-noise effect[J];石油物探;2007-02
3 Peng Cai Zhu Shijun Sun Jianku Chen Junhua Xia Ling Huang Dongshan Southwest Petroleum University,Chengdu 610500,China;Noise elimination with independent component analysis.[J];勘探地球物理进展;2007-01
4 JIAO Li-cheng1, TAN Shan1, LIU Fang2 (1- National Key Lab for Radar Signal Processing and Institute of Intelligent Information Processing, Xidian University, Xi’an 710071; 2- The School of Computer Science and Engineering, Xidian University, Xi’an 710071 );Ridgelet Theory: from Ridgelet Transform to Curvelet[J];工程数学学报;2005-05
5 Long Gang, Xiao Lei, and Chen Xuequan (Department of Electronics Engineering and Information Science, University of Science and Technology of China, Hefei 230027);Overview of the Applications of Curvelet Transform in Image Processing[J];计算机研究与发展;2005-08
6 Yang Liqiang, Song Haibin, Hao Tianvao and Jiang Weiwei.Exploration and Production ResearchInstitute, SINOPEC, Beijing 100083,China;Method of 2-D wavelet transform in attenuating random noise.[J];石油物探;2005-01
7 Wang Lihua, Institute of Geophysical Prospecting, SIN-OPEC Research Institute of Exploration and Production, Nanjing 210014,ChinaCao Hui, Tang Jinliang and Wu Yongshuan.;Noise elimination for crosswell seismic data using wavelet packet transform[J];勘探地球物理进展;2005-01
8 YI Xiang,WANG Wei-ran(College of Electronic Engineering,University of Electronic Science and Technology of China,Chengdu,Sichuan 610054,China);A Probability Model for Adaptive Image Denoising[J];电子学报;2005-01
9 Chen Xiangpeng,Key Laboratory of Geophysical Exploration, CNPC, University of Petroleum, Beijing 102249, ChinaCao Siyuan.;Second-generation wavelet transform and its application in the de-noising of seismic data.[J];石油物探;2004-06
10 Xia Hongrui, Chen Degang, Zhou Kaiming (Geophysical Branch of Jianghan Oilfield Company,Qianjiang 433100, China);Random noise elimination in seismic data processing[J];石油物探;2003-01
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved