SUI Jingkun1,2, CHEN Sheng2, ZHENG Xiaodong2, HU Tianyue1
1. School of Earth and Space Science, Peking University, Beijing 100871, China;
2. Research Institute of Petroleum Exploration and Development, PetroChina, Beijing 100083, China
Abstract:Due to the particularity and complexity of the sedimentary environment,the wave impedance difference of different reflecting boundaries in underground media may differ greatly. Weak effective reflection information of a reservoir is highly likely to be shielded by strong reflection information in seismic data and is thus difficult to recognize, which affects the identification of the reservoir. Therefore,an explanatory processing technology is urgently needed to highlight weak reflection information. In conventional methods, the strong reflection component is separated from seismic data first and then weakened or deleted. However, strong reflection residue in the subtraction method would introduce false signals in the case of inaccurate seismic wavelet extraction. This paper proposes a new idea of enhancing the weak signal and weakening the strong signal and thereby narrows the relative difference by constructing a power reflection coefficient mapping model. Firstly, the paper calculates the power reflection coefficient of the log reflection coefficient. The weak reflection coefficient is increased relatively, and the strong reflection coefficient is decreased relatively to obtain the pseudo-reflection coefficient sequence. Then, the original reflection coefficient sequence and the pseudo-reflection coefficient sequence are used for convolution operation with seismic wavelets to obtain synthesized and pseudo-synthesized seismic records,with which a training sample set can be generated. The sample set is employed to train long short-term memory (LSTM) recurrent neural networks for establishing the mapping relationship between synthesized and pseudo-synthesized seismic records. Finally, the network is applied to seismic data to enhance weak seismic reflection signals. The application of the model and actual data shows that this method effectively enhances weak reflection signals of strata and improves the ability to identify reservoirs with seismic data.
刘杰,张忠涛,刘道理,等.强反射背景下沉积体边界检测及流体识别方法[J].石油物探,2016,55(1):142-149.LIU Jie,ZHANG Zhongtao,LIU Daoli,et al.Sediment boundary identification and fluid detection for the seismic data with strong background reflections[J].Geophysical Prospecting for Petroleum,2016,55(1):142-149.
[2]
WANG Y H.Seismic time-frequency spectral decomposition by matching pursuit[J].Geophysics,2007,72(1):V13-V20.
[3]
何峰,翁斌,韩刚,等.一种基于地震约束的井控匹配追踪煤层强反射消除技术[J].中国海上油气,2019,31(1):61-66.HE Feng,WENG Bin,HAN Gang,et al.A seismic constraint-based technology for elimination of strong coal seam reflection via well-control and matching pursuit[J].China Offshore Oil and Gas,2019,31(1):61-66.
许璐,吴笑荷,张明振,等.基于局部频率约束的动态匹配追踪强反射识别与分离方法[J].石油地球物理勘探,2019,54(3):587-593.XU Lu,WU Xiaohe,ZHANG Mingzhen,et al.Strong reflection identification and separation based on the local-frequency-constrained dynamic matching pursuit[J].Oil Geophysical Prospecting,2019,54(3):587-593.
[6]
汲生珍,邬兴威,夏东领.子波分解与重构技术在储层预测中的应用[J].石油天然气学报,2013,35(11):66-69.JI Shengzhen,WU Xingwei,XIA Dongling.Application of wavelet decomposition and reconstruction technique in reservoir prediction[J].Journal of Oil and Gas Technology,2013,35(11):66-69.
[7]
AN P.Application of multi-wavelet seismic trace decomposition and reconstruction to seismic data interpretation and reservoir characterization[C].SEG Technical Program Expanded Abstracts,2006,25:973-977.
[8]
BEAR L K,PAVLIS G L.Multi-channel estimation of time residuals from broadband seismic data using multi-wavelets[J].Bulletin of the Seismological Society of America,1999,89(3):681-692.
[9]
LEBRUN J,VETTERLI M.Balanced multiwavelets theory and design[J].IEEE Transactions on Signal Proce-ssing,1998,46(4):1119-1125.
[10]
陈人杰,童思友,刘怀山,等.基于子波分解与重构的储层预测技术[J].海洋地质前沿,2014,30(1):55-61.CHEN Renjie,TONG Siyou,LIU Huaishan,et al.Reservoir prediction technology based on wavelet decomposition and reconstruction[J].Marine Geology Frontiers,2014,30(1):55-61.
[11]
佘刚,周小鹰,王箭波.多子波分解与重构法砂岩储层预测[J].西南石油大学学报(自然科学版),2013,35(1):19-27.SHE Gang,ZHOU Xiaoying,WANG Jianbo.Prediction of sand reservoir with multi-wavelet seismic trace decomposition and reconstruction[J].Journal of South-west Petroleum University (Science & Techno-logy Edition),2013,35(1):19-27.
[12]
赵爽,李仲东,许红梅,等.多子波分解技术检测含煤砂岩储层[J].天然气工业,2007(9):44-47.ZHAO Shuang,LI Zhongdong,XU Hongmei,et al.Using multiple wavelet decomposition technique to detect the sandstone reservoir with coal layer[J].Na-tural Gas Industry,2007(9):44-47.
[13]
AN P.Case studies on stratigraphic interpretation and sand mapping using volume-based seismic waveform decomposition[C].SEG Technical Program Expanded Abstracts,2006,25:496-499.
[14]
AN P.Case studies on oil and water wells separation and gas sand prediction in a coal formation using wavelet selection and volume-based seismic waveform decomposition[C].SEG Technical Program Expanded Abstracts,2008,27:498-502.
[15]
谢春临,黄伟,关晓巍,等.波形分解技术在强反射背景下薄砂层识别中的应用[J].石油地球物理勘探,2017,52(3):516-520.XIE Chunlin,HUANG Wei,GUAN Xiaowei,et al.Thin sand identification under strong reflection with volume-based waveform decomposition[J].Oil Geophysical Prospecting,2017,52(3):516-520.
[16]
田亚军,高静怀,王大兴,等.基于深度神经网络的地震强反射剥离方法[J].地球物理学报,2021,64(8):2780-2794.TIAN Yajun,GAO Jinghuai,WANG Daxing,et al.Removing strong seismic reflection based on the deep neural network[J].Chinese Journal of Geophysics,2021,64(8):2780-2794.
[17]
GUO J,WANG Y H.Recovery of a target reflection underneath coal seams[J].Journal of Geophysics & Engineering,2004,1(1):46-50.
[18]
宋建国,李赋真,徐维秀,等.改进的神经网络级联相关算法及其在初至拾取中的应用[J].石油地球物理勘探,2018,53(1):8-16.SONG Jianguo,LI Fuzhen,XU Weixiu,et al.An improved neural-network cascade-correlation algorithm and its application in seismic first break picking[J].Oil Geophysical Prospecting,2018,53(1):8-16.
[19]
庄东海,肖春燕,颜永宁.利用人工神经网络自动拾取地震记录初至[J].石油地球物理勘探,1994,29(5):659-664.ZHUANG Donghai,XIAO Chunyan,YAN Yongning.Seismic first arrivel pickup using artificial neural network[J].Oil Geophysical Prospecting,1994,29(5):659-664.
[20]
于子叶,储日升,盛敏汉.深度神经网络拾取地震P和S波到时[J].地球物理学报,2018,61(12):4873-4886.YU Ziye,CHU Risheng,SHENG Minhan.Pick onset time of P and S phase by deep neural network[J].Chinese Journal of Geophysics,2018,61(12):4873-4886.
戴前伟,江沸菠,董莉.基于汉南—奎因信息准则的电阻率层析成像径向基神经网络反演[J].地球物理学报,2014,57(4):1335-1344.DAI Qianwei,JIANG Feibo,DONG Li.RBFNN inversion for electrical resistivity tomography based on Hannan-Quinn criterion[J].Chinese Journal of Geophysics,2014,57(4):1335-1344.
[23]
陆文凯,李衍达,牟永光.误差反传播神经网络法地震反演[J].地球物理学报,1996,39(增刊1):292-301.LU Wenkai,LI Yanda,MU Yongguang.Seismic inversion using error-back-propagation neural network[J].Chinese Journal of Geophysics,1996,39(S1):292-301.
[24]
吴媚,符力耘,李维新.高分辨率非线性储层物性参数反演方法和应用[J].地球物理学报,2008,51(2):546-557.WU Mei,FU Liyun,LI Weixin.A high-resolution nonli-near inversion method of reservoir parameters and its application to oil/gas exploration[J].Chinese Journal of Geophysics,2008,51(2):546-557.
熊玄辰,曹俊兴,周鹏,等.基于双向长短期记忆神经网络的岩相预测方法[J].成都理工大学学报(自然科学版),2021,48(2):226-234.XIONG Xuanchen,CAO Junxing,ZHOU Peng,et al.Lithofacies prediction method based on bidirectional long short memory neural network[J].Journal of Chengdu University of Technology (Science & Technology Edition),2021,48(2):226-234.
[28]
张昊,朱培民,顾元,等.基于深度学习的地震速度谱自动拾取方法[J].石油物探,2019,58(5):724-733.ZHANG Hao,ZHU Peimin,GU Yuan,et al.Velocity auto-picking from seismic velocity spectra based on deep learning[J].Geophysical Prospecting for Petroleum,2019,58(5):724-733.
[29]
王俊,曹俊兴,尤加春.基于GRU神经网络的测井曲线重构[J].石油地球物理勘探,2020,55(3):510-520.WANG Jun,CAO Junxing,YOU Jiachun.Reconstruction of logging traces based on GRU neural network[J].Oil Geophysical Prospecting,2020,55(3):510-520.
[30]
邓飞,蒋沛凡,蒋先艺,等.应用图像语义分割网络的微地震事件识别和初至拾取方法[J].石油地球物理勘探,2022,57(5):1011-1019.DENG Fei,JIANG Peifan,JIANG Xianyi,et al.Microseismic event recognition and first break picking method based on image semantic segmentation network[J].Oil Geophysical Prospecting,2022,57(5):1011-1019.
[31]
罗仁泽,周洋,康丽侠,等.基于DMC-BiLSTM的沉积微相智能识别方法[J].石油物探,2022,61(2):253-261.LUO Renze,ZHOU Yang,KANG Lixia,et al.Intelligent identification of sedimentary microfacies based on DMC-BiLSTM[J].Geophysical Prospecting for Petroleum,2022,61(2):253-261.
[32]
GRAVES A,MOHAMED A R,HINTON G.Speech recognition with deep recurrent neural networks[C].2013 IEEE International Conference on Acoustics,Speech and Signal Processing,2013,6645-6649.
[33]
RICKER N.The form and laws of propagation of seismic wavelets[J].Geophysics,1953,18(1):10-40.
[34]
MA X H,XIE J,YONG R,et al.Geological characte-ristics and high production control factors of shale gas reservoirs in Silurian Longmaxi Formation,southern Sichuan Basin,SW China[J].Petroleum Exploration and Development,2020,47(5):901-915.