Abstract:The existing seismic inversion methodsare mainly model-driven and sensitive to noise, and the resolution of the inversion results is often low.In addition, they usually only use the amplitude information of seismic dataand fail to fully utilize the phase information.The results show that the correlation between wave impedance and seismic amplitude and phase is strong, so the joint application of amplitude spectrum and phase spectrum can effectively alleviate the multi-solution problem of inversion results. Therefore, this paper starts from the data-driven perspective to achieve intelligent wave impedance inversion based on frequency-phase fusion by combining deep learning with frequency (amplitude spectrum) and phase (phase spectrum) information of seismic data, which effectively improves the resolution and accuracy of inversion.The steps are as follows:①extracting the frequency and phase information of seismic trace based on the inversion of high-resolution time-frequency analysis; ②applying image processing technology to fuse frequency and phase information; ③combi-ning frequency and phase information and formation wave impedance to make data label pairs and using the data label pairs to train the preferred deep network;④extracting the frequency and phase information of the three-dimensional seismic data to be retrieved into the trained deep network, so as to obtain the high-resolution wave impedance inversion results.Compared with the existing data-driven deep learning seismic inversion methods, the innovation of the proposed method is as follows: the frequency and phase information are applied simultaneously in seismic inversion for the first time.The model test results show that the joint application of frequency and phase information can effectively alleviate the multi-solution problem of inversion results and improve the inversion accuracy.The application results in the Dalujia area of Shengli Oilfield show that compared with the traditional sparse pulse inversion, the proposed inversion method has significantly improved the longitudinal resolution, which is beneficial to further promotion and application.
IKAWA T,OHTA Y,ONISHI M,et al.An approach to seismic stratigraphic analysis[J].Journal of the Japanese Association for Petroleum Technology,1986,51(1):24-35.
RUSSELL B H.Introduction to Seismic Inversion Methods[M]. Society of Exploration Geophysicists,Tulsa,1988.
[4]
WANG Lingling,GAO Jinghuai,ZHAO Qian,et al.Relative acoustic impedance inversion via Toeplitz-Spase Matrix Factorization[J].Chinese Journal of Geophysics,2017,60(2):639-654.汪玲玲,高静怀,赵谦,等.基于矩阵Toeplitz稀疏分解的相对波阻抗反演方法[J].地球物理学报,2017,60(2):639-654.
[5]
杨培杰.地震子波盲提取与非线性反演[D].山东东营:中国石油大学, 2008.
[6]
PARTYKA G,GRIDLEY J,LOPEZ J.Interpretational applications of spectral decomposition in reservoir characterization[J].The Leading Edge,1999,18(3):353-360.
[7]
PORSANI M J,URSIN B.Mixed-phase deconvolution and wavelet estimation[J].The Leading Edge,2000,19(1):76-79
[8]
YUE Youxi, JIANG Fan, WEN Xue,et al. Compo-site attribute derived from instantaneous phase for the recognition of reflecting interface[J].Computing Techniques for Geophysical and Geochemical Exploration,2012,34(5):505-509.乐友喜,江凡,问雪,等.用于地震反射界面识别的瞬时相位复合属性[J].物探化探计算技术,2012,34(5):505-509.
YANG Peijie,LUO Hongmei,WANG Jinduo.Seismic data phase reconstruction[J].Oil Geophysical Prospecting,2019,54(3):594-599.杨培杰,罗红梅,王金铎.地震数据分相位重构方法[J].石油地球物理勘探, 2019,54(3):594-599.
[11]
LI Suhua,YU Yang,LI Rong,et al.Application of neural network inversion in prediction of volcanic rock reservoir[J].Oil Geophysical Prospecting,2023, 58(2):392-402.李素华,余洋,李蓉,等.神经网络反演在火山岩储层预测中的应用[J].石油地球物理勘探,2023,58(2):392-402.
[12]
JIN Long,CHEN Xiaohong,WANG Shoudong. Oil/gas-predicted method by seismology based on supporting vector computer and information merging[J].Oil Geophysical Prospecting,2006,41(1):76-80.金龙,陈小宏,王守东.基于支持向量机与信息融合的地震油气预测方法[J].石油地球物理勘探,2006,41(1):76-80.
DAS V,POLLACK A,WOLLNER U,et al.Convolutional neural network for seismic impedance inversion[J].Geophysics, 2019,84(6):R869-R880.
[15]
SONG Lei,YIN Xingyao,ZONG Zhaoyun,et al.Deep learning seismic impedance inversion based on prior constraints[J].Oil Geophysical Prospecting,2021,56(4):716-727.宋磊,印兴耀,宗兆云,等.基于先验约束的深度学习地震波阻抗反演方法[J].石油地球物理勘探, 2021,56(4):716-727.
[16]
ZHANG Guoyin,WANG Zhizhang,LIN Chengyan,et al. Seismic reservoir prediction method based on wavelet transform and convolutional neural network and its application[J].Journal of China University of Petroleum(Edition of Natural Science), 2020,44(4):83-93.张国印,王志章,林承焰,等.基于小波变换和卷积神经网络的地震储层预测方法及应用[J].中国石油大学学报(自然科学版),2020,44(4):83-93.
[17]
WU X,LIANG L,SHI Y,et al.FaultSeg3D:Using synthetic datasets to train an end-to-end convolutional neural network for 3D seismic fault segmentation[J].Geophysics,2019,84(3):IM35-IM45.
[18]
YAN Xingyu,GU Hanming,LUO Hongmei,et al.Intelligent seismic facies classification based on an improved deep learning method[J].Oil Geophysical Prospecting,2020,55(6):1169-1177.闫星宇,顾汉明,罗红梅,等.基于改进深度学习方法的地震相智能识别[J].石油地球物理勘探,2020,55(6):1169-1177.
[19]
WANG Di,ZHANG Yiming,ZHANG Fanchang,et al. Quantitative prediction of tight sandstone sweet spots based on deep learning method with prior information constraints[J].Oil Geophysical Prospecting,2023,58(1):65-74.王迪,张益明,张繁昌,等.利用先验信息约束的深度学习方法定量预测致密砂岩"甜点"[J].石油地球物理勘探, 2023, 58(1):65-74.
[20]
PURYEAR C I,PORTNIAGUINE O N,COBOS C M,et al.Constrained least-squares spectral analysis:Application to seismic data[J].Geophysics,2012,77(5):V143-V167.
[21]
YANG Peijie,SUI Fenggui.An improved least squares timefrequency analysis[J].Geophysical Prospecting for Petroleum, 2020,59(5):815-822.杨培杰,随风贵.一种改进的最小二乘时频分析方法[J]. 石油物探,2020,59(5):815-822.
[22]
ZHANG Shengqiang, ZHANG Zhijun,LI Yao,et al.Adaptive strong reflection separation method based on seismic phase decomposition[J].Oil Geophysical Prospecting,2021,56(6):1236-1243.张生强,张志军,李尧,等.基于地震相位分解的自适应强反射分离方法[J].石油地球物理勘探,2021,56(6):1236-1243.
[23]
LUO Hongmei,YANG Peijie,WANG Yanguang,et al.Phase-domain reservoir prediction technology:a case study of channel sand in Chengdao area,Shengli Oilfield[J].Oil Geophysical Prospecting,2022,57(5):1129-1137.罗红梅,杨培杰,王延光,等.相位域储层预测技术——以胜利油田埕岛地区河道砂为例[J].石油地球物理勘探,2022,57(5):1129-1137.
[24]
GOODFELLOW I,BENGIO Y,COURVILLE A.Deep Learning(Adaptive Computation and Machine Learning Series)[M].The MIT Press,2017.
[25]
KIM P.MATLAB Deep Learning:With Machine Learning, Neural Networks and Artificial Intelligence[M].Apress,2017.
[26]
KINGMA D P,BA J L.Adam:A method for stochastic optimization[C].ICLR2015, DOI:10.48550/arXiv.1412.6980.