|
|
Abnormal amplitude suppression method based on denoising convolutional neural network |
FAN Chengxiang1,2, GUO Hongwei3, YUAN Yijun1 |
1. School of Geophysics and Information Technology, China University of Geosciences (Beijing), Beijing 100083, China; 2. Weichai Power Co., Ltd. Weifang, Shandong 261061, China; 3. Exploration and Development Research Institute, PetroChina, Beijing 100083, China |
|
|
Abstract Abnormal amplitude of seismic data often leads to uneven spatial energy in seismic data, resulting in arc phenomenon during the prestack migration and interfering with seismic data interpretation. Therefore, suppressing abnormal amplitudes has become an important step in seismic data processing. Due to the limitation of application conditions, traditional methods fail to completely suppress abnormal amplitude while protecting effective signals. Therefore, a method for suppressing abnormal amplitude based on a denoising convolutional neural network (DnCNN) is proposed. Firstly, according to the distribution characteristics of seismic abnormal amplitude, this method builds a DnCNN structure suitable for suppressing abnormal amplitude through network improvement and optimization. Secondly, training sets with and without abnormal amplitude are produced by artificial synthesis and real data extraction. The network is trained with the training set, and a network training model that can suppress abnormal amplitude is obtained. Finally, tests on model data and real seismic data show that the proposed method can effectively suppress abnormal amplitude in seismic data, protect effective signals, and obtain better processing results than commonly used traditional methods.
|
Received: 22 August 2022
|
|
|
|
|
[1] |
苏世龙, 蔡希玲, 曾庆芹, 等. 多重约束下异常地震道自动剔除与质量监控[J]. 勘探地球物理进展, 2009, 32(5):334-341.SU Shilong, CAI Xiling, ZENG Qingqin, et al. Automatic rejection and quality control of abnormal seismic traces under multi-constraints[J]. Progress in Exploration Geophysics, 2009, 32(5):334-341.
|
[2] |
陈志德, 郑锡娟, 关昕, 等. 长垣油田地震异常振幅噪声分频压制技术[J]. 大庆石油地质与开发, 2010, 29(5):164-167.CHEN Zhide, ZHENG Xijuan, GUAN Xin, et al. Separate frequency technique for anomalous amplitude noise of the seismic data in Daqing Placanticline[J]. Petroleum Geology and Oilfield Development in Daqing, 2010, 29(5):164-167.
|
[3] |
陈海峰, 钱忠平, 刘迪, 等. "黑三角"强能量干扰分频检测与压制[C]. 中国石油学会2021年物探技术研讨会论文集, 2021, 362-365.CHEN Haifeng, QIAN Zhongping, LIU Di, et al. Frequency division detection and suppression of "black triangle" strong energy interference[C]. Proceedings of the 2021 Geophysical Exploration Technology Seminar of the Chinese Petroleum Society, 2021, 362-365.
|
[4] |
陈超群, 田媛媛, 高秦, 等. 基于随机函数数据重构的分频异常振幅衰减技术在巨厚黄土塬区的应用[J]. 石油物探, 2019, 58(5):741-749.CHEN Chaoqun, TIAN Yuanyuan, GAO Qin, et al. Frequency-division abnormal amplitude attenuation af ter data reconstruction based on random function and its application in the very thick loess tableland area, Ordos Basin[J]. Geophysical Prospecting for Petro leum, 2019, 58(5):741-749.
|
[5] |
王在民, 朱江, 李磊, 等. 振幅衰减法分频自动识别和压制异常能量道[J]. 新疆石油地质, 2011, 32(1):80-82.WANG Zaimin, ZHU Jiang, LI Lei, et al. Automatic recognition and suppression of abnormal energy seismic trace by method for amplitude attenuation and frequency division[J]. Xinjiang Petroleum Geology, 2011, 32(1):80-82.
|
[6] |
YU Z, GAROSSINO P G A. High-energy noise attenuation of seismic data in the wavelet-transform domain[J]. Integrated Computer-Aided Engineering, 2005, 12(1):57-67.
|
[7] |
DUNCAN G, BERESFORD G. Some analyses of 2D median f-k filters[J]. Geophysics, 1995, 60(4):1157-1168.
|
[8] |
冯晅, 刘财, 杨宝俊, 等. 中值滤波器对信号相位和形状影响的研究[J]. 石油物探, 2002, 41(1):37-41, 75.FENG Xuan, LIU Cai, YANG Baojun, et al. The impacts of median filter to the phases and shapes of signals[J]. Geophysical Prospecting for Petroleum, 2002, 41(1):37-41, 75.
|
[9] |
LIU Y, LIU C, WANG D. A 1D time-varying median filter for seismic random, spike-like noise elimination[J]. Geophysics, 2009, 74(1):V17-V24.
|
[10] |
ZHAO Y, LI Y, DONG X, et al. Low-frequency noise suppression method based on improved DnCNN in desert seismic data[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(5):811-815.
|
[11] |
YU S, MA J, WANG W. Deep learning for denoising[J]. Geophysics, 2019, 84(6):V333-V350.
|
[12] |
SI X, YUAN Y, SI T, et al. Attenuation of random noise using denoising convolutional neural networks[J]. Interpretation, 2019, 7(3):SE269-SE280.
|
[13] |
YUAN Y, SI X, ZHENG Y. Ground-roll attenuation using generative adversarial networks[J]. Geophysics, 2020, 85(4):WA255-WA267.
|
[14] |
MCCORMACK M D. Seismic trace editing and first break picking using neural networks[C]. SEG Technical Program Expanded Abstracts, 1990, 9:321-324.
|
[15] |
张学工, 李衍达. 用人工神经网络实现地震记录中的废道自动切除[J]. 地球物理学报, 1992, 35(5):637-643.ZHANG Xuegong, LI Yanda. Automatic editing of noisy seismic data using an artificial neural network approach[J]. Chinese Journal of Geophysics, 1992, 35(5):637-643.
|
[16] |
朱广生, 刘瑞林, 王庭阁. 神经网络在油气层横向预测和地震道编辑中的应用[J]. 石油物探, 1994, 33(1):1-9.ZHU Guangsheng, LIU Ruilin, WANG Tingge. Application of neural network to reservoir lateral prediction and trace editing[J]. Geophysical Prospecting for Petroleum, 1994, 33(1):1-9.
|
[17] |
庄东海, 肖春燕. 自动编辑地震道的两步法[J]. 江汉石油学院学报, 1995, 17(2):39-42.ZHUANG Donghai, XIAO Chunyan. An effective method for automatic editing seismic data through two steps[J]. Journal of Jianghan Petroleum Institute, 1995, 17(2):39-42.
|
[18] |
周振晓, 倪凤田, 刘建红. 神经网络自动道编辑的改进与应用[J]. 吐哈油气, 2012, 17(1):22-24.ZHOU Zhenxiao, NI Fengtian, LIU Jianhong. Improvement and application of automated trace editing with neural network[J]. Tuha Oil & Gas, 2012, 17(1):22-24.
|
[19] |
王文强, 孟凡顺, 孙文亮. 优化卷积神经网络在道编辑中的应用[J]. 地球物理学进展, 2019, 34(1):214-220.WANG Wenqiang, MENG Fanshun, SUN Wenliang. Trace editing based on optimized convolutional neural network[J]. Progress in Geophysics, 2019, 34(1):214-220.
|
[20] |
崔少华, 李素文, 汪徐德. 改进的卷积神经网络对地震数据进行去噪的方法[J]. 激光与光电子学进展, 2020, 57(6):263-270.CUI Shaohua, LI Suwen, WANG Xude. De-noising method for seismic data via improved convolution neural network[J]. Laser & Optoelectronics Progress, 2020, 57(6):263-270.
|
[21] |
IOFFE S, SZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[C]. Proceedings of the 32nd International Conference on Machine Learning, 2015, 448-456.
|
[22] |
DING X, GUO Y, DING G, et al. ACNet:Strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks[C]. 2019 IEEE/CVF International Conference on Computer Vision(ICCV), 2019, 1911-1920.
|
|
|
|