Abstract：Deep residual network,as an advanced deep learning algorithm,has received high attention from academic and industrial circles in recent years.To realize intelligent and efficient suppression of random noise in pre-stack seismic records,first,a deep nonlinear denoising network is designed based on the principle of deep residual network,and then the network is trained by the constructed high-quality random noise training sets to automatically learn the features of random noises in a high-dimensional space,so as to fit the nonlinear mapping relationship between noisy seismic records and random noises,and achieve the purpose of automatic suppression of random noises.Both model test and field application have proved the effectiveness of this method.Though the denoising capability of this method is as good as the method used for generating label data,the former has better denoising efficiency and adaptability than the latter.It provides an idea to deal with the denoising problem of TB-level pre-stack seismic data.
Zhang B,Lin T and Marfurt K.Noise suppression of time migrated gathers using prestack structure oriented filtering[C].SEG Technical Program Expanded Abstracts,2015,34:4678-4681.
[2]
Jones I F and Levy S.Signal-to-noise ratio enhancement in multichannel seismic data via the Karhunen-Loeve transform[J].Geophysical Prospecting,1987,35(1):12-32.
[3]
Harris P E and White R E.Improving the perfor-mance of f-x prediction filtering at low signal-to-noise ratios[J].Geophysical Prospecting,1997,45(2):269-302.
[4]
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,LI Zhenchun.An adaptive filtering denoising method based on generalized S-transform and Gaussian smoothing[J].Oil Geophysical Prospecting,2018,53(6):1128-1136.
[5]
Wang Y H.Antialiasing conditions in the delay-time Radon transform[J].Geophysical Prospecting,2002,50(6):665-672.
[6]
夏洪瑞,陈德刚,周开明.地震资料处理中随机干扰消除方法分析[J].石油物探,2003,42(1):93-96.XIA Hongrui,CHEN Degang,ZHOU Kaiming.Random noise elimination in seismic data processing[J].Geophysical Prospecting for Petroleum,2003,42(1):93-96.
[7]
Cao S Y and Chen X P.The second-generation wavelet transform and its application in denoising of seismic data[J].Applied Geophysics,2005,2(2):70-74.
[8]
邵婕,孙成禹,唐杰,等.基于字典训练的小波域稀疏表示微地震去噪方法[J].石油地球物理勘探,2016,51(2):254-260.SHAO Jie,SUN Chengyu,TANG Jie,et al.Micro-seismic data denoising based on sparse representations over learned dictionary in the wavelet domain[J].Oil Geophysical Prospecting,2016,51(2):254-260.
[9]
桑雨,高树生,宋宏文,等.利用奇异值分解方法提高地震数据信噪比[J].石油地球物理勘探,2014,49(增刊1):72-75.SANG Yu,GAO Shusheng,SONG Hongwen,et al.Signal to noise ratio improvement with the SVD method[J].Oil Geophysical Prospecting,2014,49(S1):72-75.
[10]
Liu X W and Gou L M.Suppressing random noise to broaden the useful bandwidth of seismic reflection data[J].Applied Geophysics,2007,4(1):37-44.
[11]
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 denoise by S transform[J].Oil Geophysical Prospecting,2007,42(4):402-406.
[12]
齐少华,刘启元,陈九辉,等.接收函数的曲波变换去噪[J].地球物理学报,2006,59(3):884-896.QI Shaohua,LIU Qiyuan,CHEN Jiuhui,et al.Atte-nuation of noise in receiver functions using curvelet transform[J].Chinese Journal of Geophysics,2006,59(3):884-896.
[13]
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.
[14]
刘洋,Fomel S,刘财,等.高阶seislet变换及其在随机噪声消除中的应用[J].地球物理学报,2009,52(8):2142-2151.LIU Yang,Fomel S,LIU Cai,et al.High-order seislet transform and its application of random noise attenuation[J].Chinese Journal of Geophysics,2009,52(8):2142-2151.
[15]
王伟,高静怀,陈文超,等.基于结构自适应中值滤波器的随机噪声衰减方法[J].地球物理学报,2012,55(5):1732-1741.WANG Wei,GAO Jinghuai,CHEN Wenchao,et al.Random seismic noise suppression via structure-adaptive median filter[J].Chinese Journal of Geophysics,2012,55(5):1732-1741.
[16]
孙哲,王建锋,王静,等.基于时空变中值滤波的随机噪声压制方法[J].石油地球物理勘探,2016,51(6):1094-1102.SUN Zhe,WANG Jianfeng,WANG Jing,et al.Random noise elimination based on the time-space variant median filtering[J].Oil Geophysical Prospecting,2016,51(6):1094-1102.
[17]
林红波,马海涛,许丽萍.压制空间非平稳地震勘探随机噪声的ROAD径向时频峰值滤波算法[J].地球物理学报,2015,58(7):2546-2555.LIN Hongbo,MA Haitao,XU Liping.A radial time-frequency peak filtering based on ROAD for suppressing spatially nonstationary random noise in seismic data[J].Chinese Journal of Geophysics,2015,58(7):2546-2555.
[18]
张岩,任伟建,唐国维.应用结构聚类字典学习压制地震数据随机噪声[J].石油地球物理勘探,2018,53(6):1119-1127.ZHANG Yan,REN Weijian,TANG Guowei.Random noise suppression on seismic data based on structured-clustering dictionary learning[J].Oil Geophysical Prospecting,2018,53(6):1119-1127.
[19]
徐彦凯,曹思远,潘晓,等.随机噪声的局部正交压制方法[J].石油地球物理勘探,2019,54(2):280-287.XU Yankai,CAO Siyuan,PAN Xiao,et al.A local orthogonalization for seismic random noise suppression[J].Oil Geophysical Prospecting,2019,54(2):280-287.
[20]
钟铁,李月,杨宝俊,等.陆地地震勘探随机噪声统计特性[J].地球物理学报,2017,60(2):655-664.ZHONG Tie,LI Yue,YANG Baojun,et al.Statistical features of the random noise in land seismic prospecting[J].Chinese Journal of Geophysics,2017,60(2):655-664.
[21]
Lecun Y,Bengio Y and Hinton G.Deep learning[J].Nature,2015,521(7553):436-444.
[22]
Hinton G,Osindero S,Teh Y.A fast learning algo-rithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.
[23]
Lewis W and Vigh D.Deep learning prior models from seismic images for full-waveform inversion[C].SEG Technical Program Expanded Abstracts,2017,36:1512-1516.
[24]
Itan L,Serfaty Y,Chase D,et al.Wavefield separation via PCA and deep learning in the local angle domain[C].SEG Technical Program Expanded Abstracts,2017,36:991-995.
[25]
Huang L,Dong X,Clee T E.A scalable deep learning platform for identifying geologic features from seismic attributes[J].The Leading Edge,2017,36(3):249-256.
[26]
Lecun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Procee-dings of the IEEE,1998,86(11):2278-2324.
[27]
Krizhevsky A,Sutskever I and Hinton G.Image net classification with deep convolutional neural networks[C].International Conference on Neural InformationProcessing Systems,2012,1097-1105.
[28]
Szegedy C,Liu W,Jia Y,et al.Going deeper with convolutions[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015,1-9.
[29]
Simonyan K and Zisserman A.Very deep convolutio-nal networks for large-scale image recognition[C].International Conference on Learning Representations,2015,1-14.
[30]
He K,Zhang X,Ren S,et al.Deep residual learning for image recognition[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016,770-778.
[31]
Zhang K,Zuo W,Chen Y,et al.Beyond a Gaussian denoiser:Residual learning of deep CNN for image denoising[J].IEEE Transactions on Image Proce-ssing,2017,26(7):3142-3155.
[32]
Yann L.Efficient backprop//Neural Networks:Tricks of the Trade[M].Springer,New York,1998,9-50.
