Prediction of S-wave velocity based on GRU neural network
SUN Yuhang1,2, LIU Yang1,2,3
1. State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum(Beijing), Beijing 102249, China; 2. CNPC Key Laboratory of Geophysical Prospecting, China University of Petroleum(Beijing), Beijing 102249, China; 3. Karamay Campus, China University of Petroleum(Beijing), Karamay, Xinjiang 834000, China
Abstract:There is a relationship between reservoir parameters and shear wave velocity.But it is too complex to get analytic solutions.This paper proposes a GRU (gated recurrent unit) neural network which includes building a neural network,data preprocessing,samples training and data predication.After approximating the relationship between S-wave velocity and reservoir parameters by training a neural network,S-wave velocity can be predicted directly from P-wave velocity,density,gamma ray,porosity and logarithm of resistivity.The neural network was trained and tested by logging data from 30 wells in Block D.The results show that: ①The P-wave velocity,density and logarithm of resistivity are positively related to the S-wave velocity,while the gamma ray and porosity are negatively related to the S-wave velocity; ②In the case of being trained by more wells and tested by less wells,the relative error between the S-wave velocity and the real one is about 3.00%,and the correlation coefficient is 0.9837 for training data,while they are 3.19% and 0.9805 for tested data.In the case of being trained by less wells and tested by more wellsg,the relative error is 2.49% and the correlation coefficient is 0.9867 for training data,while they are 3.92% and 0.9686 for testing data.The new method has a high prediction accuracy and generalization ability.
Pickett G R.Acoustic character logs and their application in formation evaluation[J].Journal of Petroleum Technology,1963,15(6):650-667.
[2]
Castagna J P,Batzle M L,Eastwood R L.Relationships between compressional-wave and shear-wave velocities in clastic silicate rocks[J].Geophysics,1985,50(4):571-581.
[3]
Han D,Nur A,Morgan D.Effect of porosity and clay content on wave velocity in sandstones[J].Geophy-sics,1986,51(11):2093-2107.
[4]
Smith G C,Gidlow P M.Weighted stacking for rock property estimation and detection of gas[J].Geophy-sical Prospecting,1987,35(9):993-1014.
[5]
Gal D,Dvorkin J,Nur A.A physical model for porosity reduction in sandstones[J].Geophysics,1998,63(2):454-459.
[6]
Dvorkin J,Prasad M,Sakai A,et al.Elasticity of marine sediments:Rock physics modeling[J].Geophysical Research Letters,1999,26(12):1781-1784.
[7]
李文成,彭嫦姿,杨鸿飞.横波预测技术在YB地区的应用[J].地球物理学进展,2014,29(4):1695-1700.LI Wencheng,PENG Changzi,YANG Hongfei.The application of S-wave predication technology in YB area[J].Progress in Geophysics,2014,29(4):1695-1700.
[8]
Xu S,White R E.A physical model for shear-wave velocity prediction[J].Geophysics,1996,44(4):687-717.
[9]
Xu S,Payne M A.Modeling elastic properties in carbonate rocks[J].The Leading Edge,2009,28(1):66-74.
[10]
刘欣欣,印兴耀,张峰.一种碳酸盐岩储层横波速度估算方法[J].中国石油大学学报(自然科学版),2013,37(1):42-49.LIU Xinxin,YIN Xingyao,ZHANG Feng.S-wave velocity estimation method in carbonate reservoir[J].Journal of China University of Petroleum(Edition of Natural Sciences),2013,37(1):42-49.
[11]
Pride S R,Berryman J G,Harris J M.Seismic attenua-tion due to wave-induced flow[J].Journal of Geophysical Research Solid Earth,2004,109(B1):247-278.
[12]
Lee M W.A simple method of predicating S-wave velocity[J].Geophysics,2006,71(6):F161-F164.
[13]
罗水亮,杨培杰,胡光明,等.基于变形P-L模型的矩阵方程迭代精细横波预测[J].地球物理学报,2016,59(5):1839-1848.LUO Shuiliang,YANG Peijie,HU Guangming,et al.S-wave velocity predication based on the modified P-L model and matrix equation iteration[J].Chinese Journal of Geophysics,2016,59(5):1839-1848.
[14]
郑旭桢,王涛,刘钊,等.泥岩基质弹性参数对Xu-White模型横波速度估算的影响[J].石油地球物理勘探,2017,52(5):990-998.ZHENG Xuzhen,WANG Tao,LIU Zhao,et al.Inf-luence of clay elastic parameters on S-wave velocity estimation based on Xu-White model[J].Oil Geophysical Prospecting,2017,52(5):990-998.
[15]
唐杰,王浩,姚振岸,等.基于岩石物理诊断的横波速度估算方法[J].石油地球物理勘探,2016,51(3):537-543.TANG Jie,WANG Hao,YAO Zhen'an,et al.Shear wave velocity estimation based on rock physics diagnosis[J].Oil Geophysical Prospecting,2016,51(3):537-543.
[16]
熊晓军,林凯,贺振华.基于等效弹性模量反演的横波速度预测方法[J].石油地球物理勘探,2012,47(5):723-727.XIONG Xiaojun,LIN Kai,HE Zhenhua.A method for S-wave velocity estimation based on equivalent elastic modulus inversion[J].Oil Geophysical Prospecting,2012,47(5):723-727.
[17]
Lipton Z C,Berkowitz J,Elkan C.A critical review of recurrent neural networks for sequence learning[J].Computer Science,2015,arXiv:1506.00019.
[18]
张国豪,刘波.采用CNN和Bidirectional GRU的时间序列分类研究[J].计算机科学与探索,2019,13(6):916-927.ZHANG Guohao,LIU Bo.Research on time series classification using CNN and Bidirectional GRU[J].Journal of Frontiers of Computer Science and Technology,2019,13(6):916-927.
Jozefowicz R,Zaremba W,Sutskever I.An empirical exploration of recurrent network architectures [C].International Conference on Machine Learning,2015,2342-2350.
[21]
Cho K,van Merrienboer B,Bahdanau D,et al.On the properties of neural machine translation: Encoder-decoder approaches[J].Computer Science,2014,doi: 10.3115/v1/W14-4012.
[22]
王维红,包培楠,陈国飞,等.基于最小平方的横波速度拟合及应用[J].地球物理学进展,2019,34(5):1924-1929.WANG Weihong,BAO Peinan,CHEN Guofei,et al.S-wave prediction and its application based on least square algorithm[J].Progress in Geophysics,2019,34(5):1924-1929.