Marine multiple attenuation method based on SA-GAN
YE Yueming1, CAO Xiaochu1, REN Haoran2, ZHANG Chunyan1
1. PetroChina Hangzhou Research Institute of Geology, Hangzhou, Zhejiang 310023, China; 2. Institute of Advanced Technology, Zhejiang University, Hangzhou, Zhejiang 310027, China
Abstract：Due to the existence of two strong wave impedance interfaces at the sea surface and the sea bottom, strong multiples are commonly developed in marine seismic data. Marine multiple attenuation runs through the whole process of marine data processing, which is one of the most important factors affecting the imaging qua- lity of marine seismic data. Multiple attenuation in complex marine conditions often requires many methods step by step in different domains.The calculation is time-consuming and multi-domain and multi-step will cause the accumulation of calculation errors, which will affect the multiple attenuation efficiency and precision.In this paper,a marine multiple attenuation method based on self-attention generative adversarial networks （SA-GAN） is proposed. Firstly, label datasets are obtained by suppressing multiples using the method step by step in diffe- rent domains.Secondly, the self-attention mechanism is introduced into the U-Net generator network, and the multiple attenuation deep learning model based on SA-GAN is constructed, with the network trained. Finally, the SA-GAN with complete training is used to suppress the whole data. The GAN of the U-Net generator with SA has fast convergence speed and stable computation, and it has better data generalization ability on seismic sample datasets. Compared with the conventional methods, the proposed method only needs to manually process a small amount of feature data, and the network can be trained to perform multiple attenuation of a large number of data in the working area, which avoids the tedious process of multi-method series combination for complex multiple attenuation and provides an efficient means for multiple attenuation of actual marine seismic data. The model and the actual data processing of the NH deep water exploration area verify the effectiveness of this method.
HAMPSON D. Inverse velocity stacking for multiple elimination[C]. SEG Technical Program Expanded Abstracts, 1986, 5:422-424.
[2]
HERRMANN P, MOJESKY T, MAGESAN M, et al. De-aliased, high-resolution radon transforms[C].SEG Technical Program Expanded Abstracts, 2000, 19:1953-1956.
[3]
GU Jianping. Improved Radon filtering technique for suppressing multiple waves and its application effect[J].Oil Geophysical Prospecting, 2003, 38(S1):38-41.顾建平. 改进的Radon滤波压制多次波技术及应用效果[J].石油地球物理勘探, 2003, 38(增刊1):38-41.
[4]
SHI Ying, WANG Weihong. Surface-related multiple suppression approach by combining wave equation prediction and hyperbolic Radon transform[J].Chinese Journal of Geophysics, 2012, 55(9):3115-3125.石颖, 王维红. 基于波动方程预测和双曲Radon变换联合压制表面多次波[J].地球物理学报, 2012, 55(9):3115-3125.
[5]
WANG Weihong, ZHANG Zhen, SHI Ying, et al. Investigation of multiple suppression by parabolic Radon transform in λ-f domain[J].Journal of Northeast Petroleum University, 2015, 39(1):17-22.王维红, 张振, 石颖, 等. λ-f域抛物Radon变换多次波压制方法[J].东北石油大学学报, 2015, 39(1):17-22.
[6]
FAN Jingwen, LI Zhenchun, SONG Xiangyu, et al. Multiple attenuation with anisotropic high resolution Radon transform[J].Oil Geophysical Prospecting, 2016, 51(4):665-669.范景文, 李振春, 宋翔宇, 等. 各向异性高分辨率Radon变换压制多次波[J].石油地球物理勘探, 2016, 51(4):665-669.
[7]
XUE Yaru, GUO Mengjun, FENG Luyu, et al. High resolution Radon transform based on the reweighted-iterative soft threshold algorithm[J].Oil Geophysical Prospecting, 2021, 56(4):736-744, 757.薛亚茹, 郭蒙军, 冯璐瑜, 等. 应用加权迭代软阈值算法的高分辨率Radon变换[J].石油地球物理勘探, 2021, 56(4):736-744, 757.
[8]
MA Jitao, LIU Shiyou, LIAO Zhen. Research on multiple attenuation using 3D high precision amplitude-preserving Radon transform[J].Oil Geophysical Prospecting, 2022, 57(3):582-592.马继涛, 刘仕友, 廖震. 三维高精度保幅Radon变换多次波压制方法[J].石油地球物理勘探, 2022, 57(3):582-592.
[9]
ROBINSON E A. Predictive decomposition of seismic traces[J].Geophysics, 1957, 22(4):767-778.
[10]
SINTON J B, WARD R W, JOEL S, et al.Suppression of long-delay multiple reflections by predictive deconvolution[J].Geophysics, 1978, 43(7):1352-1367.
[11]
LI Da, ZHAO Changlei, LIU Wei, et al. Improved combination of DWD+SRME technology for surface multiple suppression:a case study in the shallow water area of the western South China Sea[J].Geophysical Prospecting for Petroleum, 2022, 61(3):473-482.李达, 赵昌垒, 刘巍, 等. 一种改进的DWD+SRME表面多次波组合法压制技术在南海西部浅水工区的应用[J].石油物探, 2022, 61(3):473-482.
[12]
LOKSHTANOV D. Multiple suppression by single channel and multichannel deconvolution in the tau-p domain[C].SEG Technical Program Expanded Abstracts, 1995, 14:1482-1485.
[13]
LOKSHTANOV D. Suppression of water-layer multiples-from deconvolution to wave-equation approach[C]. SEG Technical Program Expanded Abstracts, 2000, 19:1981-1984.
[14]
ZHAO Changlei, YE Yueming, YAO Genshun, et al. Prediction deconvolution in linear radon domain on the application of ocean multiples attenuation[J].Progress in Geophysics, 2013, 28(2):1026-1032.赵昌垒, 叶月明, 姚根顺, 等. 线性拉东域预测反褶积在海洋多次波去除中的应用[J].地球物理学进展, 2013, 28(2):1026-1032.
[15]
VERSCHUUR D J, BERKHOUT A J, WAPE-NAAR C P A. Adaptive surface-related multiple elimination[J].Geophysics, 1992, 57(9):1166-1177.
[16]
WEGLEIN A B, GASPAROTTO F A, CARVA-LHO P M, et al. An inverse-scattering series method for attenuation multiples in seismic reflection data[J].Geophysics, 1997, 62(6):1683-2002.
[17]
JAKUBOWICZ H. Wave equation prediction and removal of interbed multiples[C]. SEG Technical Program Expanded Abstracts, 1998, 147:1527-1530.
[18]
DRAGOSET B. 3D general surface multiple prediction:an algorithm for all surveys[C]. SEG Technical Program Expanded Abstracts, 2008, 27:2426-2430.
[19]
VAN GROENESTIJN G J A, VERSCHUUR D J. Estimation of primaries and near-offset reconstruction by sparse inversion:marine data applications[J].Geophysics, 2009, 74(6):R119-R128.
[20]
ZHAO Bangliu, YONG Xueshan, GAO Jianhu, et al. Progress and development direction of PetroChina intelligent seismic processing and interpretation technology[J].China Petroleum Exploration, 2021, 26(5):12-23.赵邦六, 雍学善, 高建虎, 等. 中国石油智能地震处理解释技术进展与发展方向思考[J].中国石油勘探, 2021, 26(5):12-23.
[21]
LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J].Proceedings of the IEEE, 1998, 86(11):2278-2324.
[22]
LECUN Y, BENGIO Y, HINTON G. Deep lear- ning[J].Nature, 2015, 521(7553):436-444.
[23]
SI X, YUAN Y J, SI T H, et al. Attenuation of random noise using denoising convolutional neural networks[J].Interpretation, 2019, 7(3):SE269-SE280.
[24]
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.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.
[25]
LI Haishan, CHEN Dewu, WU Jie, et al. Pre-stack radom noise suppression with deep residual network[J].Oil Geophysical Prospecting, 2020, 55(3):493-503.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.
[26]
YU S, MA J, WANG W. Deep learning for denoising[J].Geophysics, 2019, 84(6):V333-V350.
[27]
YU Siwei, YANG Wuyang, LI Haishan, et al. Scattered ground roll intelligent attenuation based on deep learning[J].Chinese Science Bulletin, 2021, 66(18):2343-2354.于四伟, 杨午阳, 李海山, 等. 基于深度学习的地震散射面波智能压制方法[J].科学通报, 2021, 66(18):2343-2354.
[28]
SONG Huan, MAO Weijian, TANG Huanhuan. Application of deep neural networks for multiples attenuation[J].Chinese Journal of Geophysics, 2021, 64(8):2795-2808.宋欢, 毛伟建, 唐欢欢. 基于深层神经网络压制多次波[J].地球物理学报, 2021, 64(8):2795-2808.
[29]
LIU Xiaozhou, HU Tianyue, LIU Tao, et al. Seismic internal multiple suppression method with encoder-decoder convolutional network based on data augmentation[J].Oil Geophysical Prospecting, 2022, 57(4):757-767.刘小舟, 胡天跃, 刘韬, 等. 数据增广的编解码卷积网络地震层间多次波压制方法[J].石油地球物理勘探, 2022, 57(4):757-767.
[30]
ZHANG Meng. A multiple suppression method based on self-attention convolutional auto-encoder[J].Geophysical Prospecting for Petroleum, 2022, 61(3):454-462.张猛. 基于自注意力机制的卷积自编码器多次波压制方法[J].石油物探, 2022, 61(3):454-462.
