Random and Coherent Noise Suppression in DAS-VSP Data by Using a Supervised Deep Learning Method

被引:287
作者
Dong, Xintong [1 ]
Li, Yue [1 ]
Zhong, Tie [2 ]
Wu, Ning [1 ]
Wang, Hongzhou [1 ]
机构
[1] Jilin Univ, Coll Commun Engn, Dept Informat, Changchun 130012, Peoples R China
[2] Northeast Elect Power Univ, Dept Commun Engn, Coll Elect Engn, Jilin 132012, Jilin, Peoples R China
基金
中国国家自然科学基金;
关键词
Signal to noise ratio; Data models; Noise measurement; Mathematical model; Training data; Noise reduction; Training; Convolutional neural network (CNN); distributed fiber-optical acoustic sensing (DAS); noise suppression; signal-to-noise ratio (SNR); vertical seismic profile (VSP); LOW-FREQUENCY NOISE; RATIO;
D O I
10.1109/LGRS.2020.3023706
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Distributed fiber-optical acoustic sensing (DAS) is a new and booming technology in seismic exploration. DAS technology has been gradually applied to the exploration of vertical seismic profile (VSP) due to its strong resistance to high temperature and pressure, high sensitivity, high precision (trace interval can be accurate to about 1 m), and so on. However, real DAS-VSP data are always contaminated by both random and coherent noises, which greatly affects the quality of DAS-VSP data. In order to suppress the background noise and increase the signal-to-noise ratio (SNR), a convolutional neural network (CNN) based on leaky rectifier linear unit (ReLU) and forward modeling is proposed and named L-FM-CNN. In terms of network architecture, Leaky ReLU is adopted as the activation function of CNN, which can enhance the recovery ability of trained CNN denoising model to the weak effective signals. As for the training data set, we construct a high-authenticity theoretical pure seismic data set for DAS-VSP data through the complexity of forward models and the diversification of physical parameters. In addition, we propose a new mean square error (MSE) loss function combined with an energy ratio matrix (ERM). The ERM can adjust the SNR between the signal patch and noise patch during the network training and thus increase the robustness of trained CNN denoising model for the DAS-VSP data with different SNRs, especially the DAS-VSP data with extremely low SNR. Both synthetic and real experiments prove the effectiveness of the proposed L-FM-CNN.
引用
收藏
页数:5
相关论文
共 15 条
[1]   Normalized differential method for improving the signal-to-noise ratio of a distributed acoustic sensor [J].
Ashry, Islam ;
Mao, Yuan ;
Alias, Mohd Sharizal ;
Ng, Tien Knee ;
Hveding, Frode ;
Arsalan, Muhammad ;
Ooi, Boon S. .
APPLIED OPTICS, 2019, 58 (18) :4933-4938
[2]   Random and coherent noise attenuation by empirical mode decomposition [J].
Bekara, Maiza ;
van der Baan, Mirko .
GEOPHYSICS, 2009, 74 (05) :V89-V98
[3]   Vertical seismic profiling using distributed acoustic sensing with scatter-enhanced fibre-optic cable at the Cu-Au New Afton porphyry deposit, British Columbia, Canada [J].
Bellefleur, Gilles ;
Schetselaar, Ernst ;
Wade, Devin ;
White, Don ;
Enkin, Randolph ;
Schmitt, Doug R. .
GEOPHYSICAL PROSPECTING, 2020, 68 (01) :313-333
[4]   Convolutional neural network for seismic impedance inversion [J].
Das, Vishal ;
Pollack, Ahinoam ;
Wollner, Uri ;
Mukerji, Tapan .
GEOPHYSICS, 2019, 84 (06) :R869-R880
[5]   Desert low-frequency noise suppression by using adaptive DnCNNs based on the determination of high-order statistic [J].
Dong, X. T. ;
Li, Y. ;
Yang, B. J. .
GEOPHYSICAL JOURNAL INTERNATIONAL, 2019, 219 (02) :1281-1299
[6]   New Suppression Technology for Low-Frequency Noise in Desert Region: The Improved Robust Principal Component Analysis Based on Prediction of Neural Network [J].
Dong, Xintong ;
Zhong, Tie ;
Li, Yue .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (07) :4680-4690
[7]   Signal-to-noise ratio enhancement for 3C downhole microseismic data based on the 3D shearlet transform and improved back-propagation neural networks [J].
Dong, Xintong ;
Jiang, Hong ;
Zheng, Sheng ;
Li, Yue ;
Yang, Baojun .
GEOPHYSICS, 2019, 84 (04) :V245-V254
[8]  
Ioffe S, 2015, PR MACH LEARN RES, V37, P448
[9]   Seismic Signal Denoising Using f-x Variational Mode Decomposition [J].
Liu, Wei ;
Duan, Zhongyu .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2020, 17 (08) :1313-1317
[10]   Reverse time migration of 3D vertical seismic profile data [J].
Shi, Ying ;
Wang, Yanghua .
GEOPHYSICS, 2016, 81 (01) :S31-S38