基于深度学习的地震随机噪声衰减方法研究进展

doi:10.13810/j.cnki.issn.1000-7210.2023.05.023

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (9537 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract This paper analyzes the concept, development status, method principle, denoising performance, and advantages and disadvantages of deep learning methods represented by a convolutional neural network (CNN), denoised convolutional neural network (DnCNN), U-net deep neural network, forward feedback (BP) neural network, Dilated convolutional neural network (DCNN), residual network (ResNet), and transfer learning.The denoising effects of traditional denoising methods, dictionary learning, and deep learning methods are compared, and the development prospect of deep learning technology in the field of seismic denoising is forecasted. The following conclusions are obtained:①The actual denoising effect of the deep learning method is better than that of traditional methods and dictionary learning methods.It does not need to set the structural model and has stronger generalization, shorter computation time, and higher precision.②There are many shortcomings in deep learning methods:The denoising effect of actual data is often worse than that of synthetic data; the universality is not strong; the "black box" characteristic of the neural network makes its physical interpretability greatly reduced.Network performance is closely related to the generalization of training data.The data sets used to train the network vary from person to person, making it difficult to evaluate network performance.③It is expected that deep learning will make progress and breakthroughs in the following aspects:building a denoised neural network structure suitable for different noises and introducing a better network structure to suppress seismic random noise, constructing the loss function of the network by converting the seismic signal to the transform domain, improving the learning strategy and making a more representative data set, making training data cover all solutions as much as possible, enhancing network generalization, and achieving automatic parameter tuning and methods combining model-driven and data-driven features.

Key words： model-driven data-driven deep learning dictionary learning random noise suppression convolutional neural network research progress

Received: 17 October 2022

PACS:

P631

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	CUI Yang
	WANG Yannan
	CHEN Wanli
	ZHANG Hong
	ZHU Dandan
	BAI Min

Cite this article:

CUI Yang,WANG Yannan,CHEN Wanli等. Research progress of random noise attenuation methods for seismic data based on deep learning[J]. OGP, 2023, 58(5): 1269-1283.

URL:

http://www.ogp-cn.com/EN/10.13810/j.cnki.issn.1000-7210.2023.05.023 OR http://www.ogp-cn.com/EN/Y2023/V58/I5/1269

[1]	陈旭.分数傅里叶变换在地震资料处理中的应用初探[D].吉林长春:吉林大学, 2009.
[2]	DEIGHAN A J, WATTS D R.Groun-roll suppression using the wavelet transform[J].Geophysics, 1997, 62(6):1896-1903.
[3]	王振国, 周熙襄, 李晶.基于小波变换的最小光滑滤波去噪[J].石油地球物理勘探, 2002, 37(6):594-600.WANG Zhenguo, ZHOU Xixiang, LI Jing.Noise attenuation using minimum smooth filter based on wavelet transform[J].Oil Geophysical Prospecting, 2002, 37(6):594-600.
[4]	李继伟, 臧殿光, 刁永波, 等.自适应相减和Curvelet变换组合压制面波[J].石油地球物理勘探, 2020, 55(5):1005-1015.LI Jiwei, ZANG Dianguang, DIAO Yongbo, et al.Combination of adaptive subtraction and Curvelet transform to suppress surface waves[J].Oil Geophysical Prospecting, 2020, 55(5):1005-1015.
[5]	FOMEL S.Towards the seislet transform[C].SEG Technical Program Expanded Abstracts, 2006, 25:2847-2851.
[6]	刘洋, FOMELSergey, 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 Sergey, 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.
[7]	邓心欢.自适应时频峰值滤波压制地震勘探随机噪声[D].吉林长春:吉林大学, 2016.
[8]	胡瑞卿, 何俊杰, 李华飞, 等.时频域变分模态分解地震资料去噪方法[J].石油地球物理勘探, 2021, 56(2):257-264.HU Ruiqing, HE Junjie, LI Huafei, et al.Seismic data de-noising method based on VMD in time-frequency domain[J].Oil Geophysical Prospecting, 2021, 56(2):257-264.
[9]	WANG C, ZHU Z, GU H, et al. Hankel low-rank approximation for seismic noise attenuation[J].IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(1):561-573.
[10]	刘璐, 刘洋, 刘财, 等.地震随机噪声压缩感知迭代压制方法[J].地球物理学报, 2021, 64(12):4629-4643.LIU Lu, LIU Yang, LIU Cai, et al.Iterative seismic random noise suppression method based on compressive sensing[J].Chinese Journal of Geophysics, 2021, 64(12):4629-4643.
[11]	耿瑜, 吴如山, 高静怀.基于Dreamlet变换的地震数据压缩理论与方法[J].地球物理学报, 2012, 55(8):2705-2715.GENG Yu, WU Rushan, GAO Jinghuai.Dreamlet compression of seismic data[J].Chinese Journal of Geophysics, 2012, 55(8):2705-2715.
[12]	PORSANI M J, URSIN B.Deconvolution and wavelet estimation by using a genetic algorithm[C].SEG Technical Program Expanded Abstracts, 2000, 19:2185-2188.
[13]	程文婷, 方文倩, 付丽华.基于自相似性和低秩先验的地震数据随机噪声压制[J].石油物探, 2020, 59(6):880-889.CHENG Wenting, FANG Wenqian, FU Lihua.Seismic noise suppression via self-similarity and low-rank prior[J]. Geophysical Prospecting for Petroleum, 2020, 59(6):880-889.
[14]	DONOHO D L.Compressed sensing[J].IEEE Transactions on Information Theory, 2006, 52(4):1289-1306.
[15]	唐刚.基于压缩感知和稀疏表示的地震数据重建与去噪[D].北京:清华大学, 2010.
[16]	AHARON M, ELAD M, BRUCKSTEIN A.K-SVD:An algorithm for designing overcomplete dictionaries for sparse representation[J].IEEE Transactions on Signal Processing, 2006, 54(11):4311-4322.
[17]	TANG G, MA J, YANG H.Seismic data denoising based on learning-type overcomplete dictionaries[J].Applied Geophysics, 2012, 9(1):27-32.
[18]	BECKOUCHE S, MA J.Simultaneous dictionary learning and denoising for seismic data[J].Geophysics, 2014, 79(3):A27-A31.
[19]	宋维琪, 弓震, 王超, 等.基于K-SVD字典学习方法的地震资料去噪[J/OL].地球物理学进展, 2020(2020-06-08)[2022-05-03].https://kns.cnki.net/kcms/detail/11.2982.P.20200608.1134.066.html.
[20]	WU J, CEHN Q, GUI Z, et al.Fast dictionary learning for 3D simultaneous seismic data reconstruction and denoising[J].Journal of Applied Geophysics, 2021, doi:10.1016/j.jappgeo.2021.104446.
[21]	LECUN Y, BOTTOU L.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE, 1998, 86(11):2278-2324.
[22]	ZHANG K, ZUO W, CHEN Y, et al.Beyond a Gaus-sian denoiser:Residual learning of deep CNN for image denoising[J].IEEE Transactions on Image Processing, 2016, 26(7):3142-3155.
[23]	RONNEBERGER O, FISCHER P, BROX T.U-Net:convolutional networks for biomedical image segmentation[C].Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015, 2015, 234-241.
[24]	RUMELHART D E, HINTON G E, WILLIAMS R J.Learning representations by back propagating errors[J].Nature, 1986, 323(6088):533-536.
[25]	LI Y, ZHANG X, CHEN D.CSRNET:Dilated convolutional neural networks for understanding the highly congested scenes[C]. Proceedings-2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, 1091-1100.
[26]	HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C].Proceedings-2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016, 770-778.
[27]	TURING A M. Computing machinery and intelligence[J]. Mind, 1950, doi:10.1093/mind/lix.236.433.
[28]	KRIZHEVSKY A, SUTSKEVER I, HINTON G E.ImageNet classification with deep convolutional neural networks[J].Communication of the ACM, 2017, 60(6):84-90.
[29]	SIMONYAN K, ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].2014, doi:10.48550/arXiv.1409.1556.
[30]	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):862-869.HAN Weixue, ZHOU Yatong, CHI Yue.Deep learning convolutional neural networks for random noise attenuation in seismic data[J].Geophysical Prospecting for Petroleum, 2018, 57(6):862-869.
[31]	ZHANG M, LIU Y, CHEN Y.Unsupervised seismic random noise attenuation based on deep convolutional neural network[J].IEEE Access, 2019, 7:179810-179822.
[32]	DONG X, ZHONG T, LI Y.New suppression technology for low-frequency noise in desert region:The improved robust principal component analysis based on prediction of neural network[J].IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(7):4680-4690.
[33]	YANG L, CHEN W, LIU W, et al.Random noise attenuation based on residual convolutional neural network in seismic datasets[J].IEEE Access, 2020, 8:30271-30286.
[34]	向奎.基于卷积神经网络的地震资料去噪方法研究[D].北京:中国石油大学(北京), 2018.
[35]	DONG C, LOY C C, HE K, et al.Image super-resolution using deep convolutional networks[J].IEEE Transaction on Pattern Analysis Machine Intelligence, 2016, 38(2):295-307.
[36]	FANG W, FU L, LI H.Unsupervised CNN based on self-similarity for seismic data denoising[J].IEEE Geoscience and Remote Sensing Letters, 2021, doi:10.1109/LGRS.2021.3131046.
[37]	CHEN G, LIU Y, ZHANG M, et al.Dropout-based robust self-supervised deep learning for seismic data denoising[J].IEEE Geoscience and Remote Sensing Letters, 2022, doi:10.1109/LGRS.2022.3167999.
[38]	WANG F, YANG B, WANG Y, et al.Learning from noisy data:An unsupervised random denoising method for seismic data using model-based deep learning[J].IEEE Transactions on Geoscience and Remote Sensing, 2022, doi:10.1109/TGRS.2022.3165037.
[39]	FENG J, LI X, LIU X, et al.Multigranularity feature fusion convolutional neural network for seismic data denoising[J].IEEE Transactions on Geoscience and Remote Sensing, 2021, doi:10.1109/TGRS.2021. 3123509.
[40]	XU Q, ZHANG C, ZHANG L.Denoising convolutional neural network[C].2015 IEEE International Conference on Information & Automation, 2015, 1184-1187.
[41]	YU S, MA J, WANG W.Deep learning for denoising[J]. Geophysics, 2019, 84(6):V333-V350.
[42]	张超铭, 文晓涛, 张晓琦, 等.基于DnCNN与约束卷积的地震数据去噪方法[J/OL].地球物理学进展, 2022(2022-03-18)[2022-03-30].https://kns.cnki.net/kcms/detail/11.2982.P.20220316.1806.032.html.
[43]	钟铁, 陈云, 董新桐, 等.基于DBBCNN的沙漠区地震资料随机噪声衰减方法[J].石油地球物理勘探, 2022, 57(2):268-278.ZHONG Tie, CHEN Yun, DONG Xintong, et al.Research on random noise attenuation method for seismic data from deserts based on DBBCNN[J].Oil Geophysical Prospecting, 2022, 57(2):268-278.
[44]	ZHONG T, CHENG M, DONG X, et al.Seismic random noise attenuation by applying multiscale denoising convolutional neural network[J].IEEE Transactions on Geoscience and Remote Sensing, 2021, doi:10.1109/TGRS.2021.3095922.
[45]	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):421-433.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):421-433.
[46]	罗仁泽, 李阳阳.一种基于RUnet卷积神经网络的地震资料随机噪声压制方法[J].石油物探, 2020, 59(1):51-59.LUO Renze, LI Yangyang.Random seismic noise attenuation based on RUnet convolutional neural network[J].Geophysical Prospecting for Petroleum, 2020, 59(1):51-59.
[47]	BAI T, ZHAO H, WANG Z.A U-Net based deep learning approach for seismic random noise suppression[C].IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium, 2022, 6165-6168.
[48]	LIU N,WANG J,GAO J,et al.Similarity-informed self-learning and its application on seismic image denoising[J].IEEE Transactions on Geoscience and Remote Sensing,2022,doi:10.1109/TGRS.2022. 3210217.
[49]	LIU N, WANG J, GAO J, et al.NS2NS:Self-learning for seismic image denoising[J].IEEE Transactions on Geoscience and Remote Sensing, 2022, doi:10.1109/TGRS.2022.3217289.
[50]	顾航.基于卷积神经网络的地震数据去噪研究[D].黑龙江大庆:东北石油大学, 2019.
[51]	玉琨.基于对称式空洞卷积神经网络的地震资料去噪方法研究[D].四川成都:成都理工大学, 2020.
[52]	何凯.隔震结构地震响应分析及抗震性能研究[D].湖北武汉:华中科技大学, 2015.
[53]	方文倩, 李志明.基于双重残差网络的地震数据随机噪声压制[J].工程地球物理学报, 2021, 18(1):44-50.FANG Wenqian, LI Zhiming.Random noise attenuation in seismic data based on dual residual networks[J].Chinese Journal of Engineer Geophysics, 2021, 18(1):44-50.
[54]	武国宁, 于萌萌, 王君仙, 等.应用平稳小波变换与深度残差网络压制地震随机噪声[J].石油地球物理勘探, 2022, 57(1):43-51.WU Guoning, YU Mengmeng, WANG Junxian, et al.Seismic random noise attenuation based on stationary wavelet transform and deep residual neural network[J].Oil Geophysical Prospecting, 2022, 57(1):43-51.
[55]	GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[J].Communications of the ACM, 2020, 63(11):139-144.
[56]	SUN H, YANG F, MA J.Seismic random noise attenuation via self-supervised transfer learning[J].IEEE Geoscience and Remote Sensing Letters, 2022, doi:10.1109/LGRS.2022.3146173.
[57]	BATSON J, ROYER L.Noise2self:Blind denoising by self-supervision[C].Proceedings of the 36th International Conference on MachineLearning, 2019, 524-533.
[58]	ZHANG M, LIU Y, CHEN Y. Unsupervised seismic random noise attenuation based on deep convolutional neural network[J].IEEE Access, 2019, 7:179810-179822.
[59]	XU W, ZHOU Y, LIU D, et al.Seismic intelligent deblending via plug and play method with blended CSGs trained deep CNN Gaussian denoiser[J].IEEE Transactions on Geoscience and Remote Sensing, 2022, doi:10.1109/TGRS.2022.3166029.
[60]	SHAO D, ZHAO Y, LI Y, et al. Noisy2Noisy:Denoise pre-stack seismic data without paired training data with labels[J].IEEE Geoscience and Remote Sen-sing Letters, 2022, doi:10.1109/LGRS.2022. 3145835.