Random noise suppression method of seismic data based on CycleGAN
WU Xuefeng1,2, ZHANG Huixing1,2
1. Key Lab of Submarine Geosciences and Prospecting Techniques, Ministry of Education, Ocean University of China, Qingdao, Shandong 266100, China; 2. Evaluation and Detection Technology Laboratory of Marine Mineral Resources, Qingdao National Laboratory for Marine Science and Technology, Qingdao, Shandong 266100, China
Abstract：Suppressing random noise and enhancing the signal-to-noise ratio (SNR) are the primary tasks in seismic data processing. As for random noise in seismic data, we proposed a suppression method based on cycle-consistent generative adversarial networks (CycleGAN). The CycleGAN was composed of two generators and two discriminators. We took Resnet as the generator to learn the chara-cteristic mapping between noise-containing data and noise-free data, thereby preventing network degradation, and PatchGAN as the discriminator to improve the resolution and accuracy of the network. Besides traditional adversarial loss, the cycle consistency loss was added to improve the stability of network training. After network construction, network parameters were adjusted according to theoretical and actual data for network training and testing, and the SNR and root mean square error of data before and after denoising are analyzed. In addition, the frequency spectrum of single-channel data was calculated to analyze the denoising results. The test results based on theoretical and practical data demonstrate that the proposed method can remove random noise in seismic data, with better denoising results than those of the wavelet threshold method, which proves the feasibility of the proposed method.
Gan S W, Wang S D, Chen Y K, et al.Improved random noise attenuation using f-x empirical mode decomposition and local similarity[J]. Applied Geophy-sics, 2016, 13(1):127-134.
[3]
国胧予, 刘财, 刘洋, 等.基于f-x域流式预测滤波器的地震随机噪声衰减方法[J]. 地球物理学报, 2020, 63(1):329-338.GUO Longyu, LIU Cai, LIU Yang, et al.Seismic random noise attenuation based on streaming prediction filter in the f-x domain[J]. Chinese Journal of Geophysics, 2020, 63(1):329-338.
[4]
赵淑红, 朱光明.S变换时频滤波去噪方法[J]. 石油地球物理勘探, 2007, 42(4):402-406.ZHAO Shuhong, ZHU Guangming. Time frequency filtering to denoising by S transorm[J]. Oil Geophysical Prospecting, 2007, 42(4):402-406.
[5]
曹鹏涛, 张敏, 李振春.基于广义S变换及高斯平滑的自适应滤波去噪方法[J]. 石油地球物理勘探, 2018, 53(6):1128-1136.CAO Pengtao, ZHANG Min and LI Zhenchun.An adaptive filtering denoising method based on genera-lized S-transform and Gaussian smoothing[J]. Oil Geophysical Prospecting, 2018, 53(6):1128-1136.
[6]
孙苗苗, 李振春, 曲英铭, 等.基于曲波域稀疏约束的OVT域地震数据去噪方法研究[J]. 石油物探, 2019, 58(2):208-218.SUN Miaomiao, LI Zhenchun, QU Yingming, et al.A seismic denoising method based on curvelet transform with sparse constraint in OVT domain[J]. Geophysical Prospecting for Petroleum, 2019, 58(2):208-218.
[7]
张华, 刁塑, 温建亮, 等.应用二维非均匀曲波变换压制地震随机噪声[J]. 石油地球物理勘探, 2019, 54(1):16-23.ZHANG Hua, DIAO Su, WEN Jianliang, et al.A random noise suppression with 2D non-uniform curvelet transform[J]. Oil Geophysical Prospecting, 2019, 54(1):16-23.
[8]
Donoho D L.De-nosing by soft-thresholding[J]. IEEE Transactions on Information Theory, 1995, 41(3):613-627.
[9]
张宇, 张关泉.小波变换用于去除高频随机噪声[J]. 石油地球物理勘探, 1997, 32(3):327-337.ZHANG Yu, ZHANG Guanquan.High-frequency random noise elimination using wavelet transform[J]. Oil Geophysical Prospecting, 1997, 32(3):327-337.
[10]
王勇, 郦军, 张奎凤.基于小波变换的地震信号降噪处理[J]. 石油物探, 1998, 37(3):72-76.WANG Yong, LI Jun, ZHANG Kuifeng.The noise elimination processing of seismic signal based on wavelet transform[J]. Geophysical Prospecting for Petroleum, 1998, 37(3):72-76.
[11]
付燕.基于二次小波变换的地震信号去噪方法[J]. 石油地球物理勘探, 2005, 40(2):154-157.FU Yan.Noise-elimination method for seismic signal based on second wavelet transform[J]. Oil Geophysical Prospecting, 2005, 40(2):154-157.
[12]
刘军, 郑成龙, 吴新华, 等.基于改进混沌果蝇优化小波阈值法地震信号随机噪声压制[J]. 地质与勘探, 2017, 53(4):765-772.LIU Jun, ZHENG Chenglong, WU Xinhua, et al. Suppression of seismic random noise based on the improved wavelet threshold method using chaotic fruit fly optimization[J]. Geology and Exploration, 2017, 53(4):765-772.
[13]
夏洪瑞, 葛川庆, 彭涛.小波时空变阈值去噪方法在可控震源资料处理中的应用[J]. 石油地球物理勘探, 2010, 45(1):23-27.XIA Hongrui, GE Chuanqing, PENG Tao.Application of wavelet time-space-varying threshold denoising method in vibroseis data processing[J]. Oil Geophysical Prospecting, 2010, 45(1):23-27.
[14]
赵迎, 乐友喜, 黄健良, 等.CEEMD与小波变换联合去噪方法研究[J]. 地球物理学进展, 2015, 30(6):2870-2877.ZHAO Ying, YUE Youxi, HUANG Jianliang, et al. CEEMD and wavelet transform jointed denoising method[J]. Progress in Geophysics, 2015, 30(6):2870-2877.
[15]
韩卫雪, 周亚同, 池越.基于深度学习卷积神经网络的地震数据随机噪声去除[J]. 石油物探, 2018, 57(6):72-79.HAN Weixue, ZHOU Yatong, CHI Yue.Deep lear-ning convolutional neural networks for random noise attenuation in seismic data[J]. Geophysical Prospecting for Petroleum, 2018, 57(6):72-79.
[16]
王钰清, 陆文凯, 刘金林, 等.基于数据增广和CNN的地震随机噪声压制[J]. 地球物理学报, 2019, 62(1):427-439.WANG Yuqing, LU Wenkai, LIU Jinlin, et al.Random seismic noise attenuation based on data augmentation and CNN[J]. Chinese Journal of Geophysics, 2019, 62(1):427-439.
[17]
李海山, 陈德武, 吴杰, 等.叠前随机噪声深度残差网络压制方法[J]. 石油地球物理勘探, 2020, 55(3):493-503.LI Haishan, CHEN Dewu, WU Jie, et al.Pre-stack random noise suppression with residual network[J]. Oil Geophysical Prospecting, 2020, 55(3):493-503.
[18]
梁俊杰, 韦舰晶, 蒋正锋.生成对抗网络GAN综述[J]. 计算机科学与探索, 2020, 14(1):1-17.LIANG Junjie, WEI Jianjing, JIANG Zhengfeng. Generative adversarial networks GAN overview[J]. Journal of Forntiers of Computer Science and Technology, 2020, 14(1):1-17.
[19]
Goodfellow I J, Pouget Abadie J, Mirza M, et al. Ge-nerative adversarial nets[C]. International Conference on Neural Information Processing Systems, 2014, 2672-2680.
[20]
杨懿男, 齐林海, 王红, 等.基于生成对抗网络的小样本数据生成技术研究[J]. 电力建设, 2019, 40(5):71-77.YANG Yinan, QI Linhai, WANG Hong, et al. Research on generation technology of small sample data based on generative adversarial network[J]. Electric Power Construction, 2019, 40(5):71-77.
[21]
桑亮, 高爽, 尹增山.基于生成对抗网络的运动模糊图像复原[J]. 计算机工程与应用, 2019, 55(6):173-177.SANG Liang, GAO Shuang, YIN Zengshan.Motion deblurring based on generative adversarial networks[J]. Computer Engineering and Applications, 2019, 55(6):173-177.
[22]
Wang H, Li Y, DONG X.Generative adversarial network for desert seismic data denoising[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020.doi:10.1109/TGRS.2020.3030692.
[23]
Dong X T, LI Y.Denoising the optical fiber seismic data by using convolutional adversarial network based on loss balance[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020.doi:10.1109/TGRS.2020. 3036065.
[24]
Radford A, Metz L, Chintala S.Unsupervised representation learning with deep convolutional generative adversarial networks[C]. Machine Learning, 2016.arXiv.org > cs > arXiv:1511.06434.
[25]
Zhu J Y, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]. IEEE International Conference on Computer Vision, 2017, 2242-2251.
[26]
Ratliff L J, Burden S A, Sastry S S. Characterization and computation of local Nash equilibria in continuous games[C]. Communication, Control, & Computing, 2006, 917-924.
[27]
刘华超, 张俊然, 刘云飞. 引入特征损失对CycleGAN的影响研究[J]. 计算机工程与应用, 2020, 56(22):217-223.LIU Huachao, ZHANG Junran, LIU Yunfei. The influence of identity loss on CycleGAN[J]. Computer Engineering and Applications, 2020, 56(22):217-223.
[28]
Li C Y, Liu H, Chen C Y, et al.ALICE:towards understanding adversarial learning for joint distribution matching[C]. 31st Annual Conference on Neural Information Processing Systems (NIPS), 2017, 1-13.
[29]
He K M, Zhang X Y, Ren S Q, et al.Deep residual learning for image recognition[C]. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016, 770-778.
[30]
Isola P, Zhu J Y, Zhou T, et al.Image-to-image translation with conditional adversarial networks[C]. Proceedings of the IEEE Computer Vision and Pattern Recognition, 2017, 1125-1134.
