基于神经网络的随机地震反演方法
|
摘要
针对随机地震反演中存在的两个主要问题,随机实现含有噪声和难以从大量随机实现中挖掘有效信息,提出了一种基于神经网络的随机地震反演方法.通过对多组随机实现及其正演地震数据的计算,构建了基于序贯高斯模拟的训练集.这也为应用神经网络求解地球物理反问题,提供了一种有效建立训练集的方法.较之传统的神经网络反演,这种训练集不仅保证了学习样本具有多样性,同时还引入了空间相关性.数值模拟结果表明,该方法只需要通过单层前馈神经网络,就可以比较有效的解决一个500个阻抗参数的反演问题.
In view of two principal problems in stochastic seismic inversion,stochastic realizations with massive noise and being difficult to dig effective information out of mass of realizations,we propose a novel stochastic seismic inversion method based on neural network.Through the simulation of stochastic realizations and the corresponding seismic forward modeling,we build the training sets based on Sequential Gaussian Simulation(SGS).It provides an effective method to establish training sets for neural network in solving geophysical inverse problems.Compared with traditional neural network algorithms,such training sets not only have the diversity of the learning samples,but also possess the spatial correlation.The numerical simulation results show that with the aid of the proposed method,we can solve an impedance inversion problem with 500 parameters by using a feed forward neural network with only one hidden layer.
In view of two principal problems in stochastic seismic inversion,stochastic realizations with massive noise and being difficult to dig effective information out of mass of realizations,we propose a novel stochastic seismic inversion method based on neural network.Through the simulation of stochastic realizations and the corresponding seismic forward modeling,we build the training sets based on Sequential Gaussian Simulation(SGS).It provides an effective method to establish training sets for neural network in solving geophysical inverse problems.Compared with traditional neural network algorithms,such training sets not only have the diversity of the learning samples,but also possess the spatial correlation.The numerical simulation results show that with the aid of the proposed method,we can solve an impedance inversion problem with 500 parameters by using a feed forward neural network with only one hidden layer.
引文
Badd ari K,A6fa T,Djarfour N,et al.2009.Application of a radial basis function artificial neural network to seismic data inversion.Computers&Geosciences,35(12):2338-2344,doi:10.1016/j.cageo.2009.03.006.
Cheng Q S,Chen R,Li T H.1996.Simultaneous wavelet estimation and deconvolution of reflection seismic signals.IEEE Transactions on Geoscience and Remote Sensing,34(2):377-384,doi:10.1109/36.485115.
Deutsch C V,Cockerham P W.1994.Practical considerations in the application of simulated annealing to stochastic simulation.Mathematical Geology,26(1):67-82:doi:10.1007/BF02065876.
Deutsch C V,Journel A G.1994.The application of simulated annealing to stochastic reservoir modeling.SPE Advanced Technology Series,2(2):222-227,doi:10.2118/24754-PA.
Dubrule O,Thibaut M,Lamy P,et al.1998.Geostatistical reservoir characterization constrained by 3Dseismic data.Petroleum Geoscience,4(2):121-128,doi:10.1144/petgeo.4.2.121.
Fu L Y.2004.Joint inversion of seismic data for acoustic impedance.Geophysics,69(4):994-1004,doi:10.1190/1.1778242.
Haas A,Dubrule O.1994.Geostatistical inversion-a sequential method of stochastic reservoir modelling constrained by seismic data.First Break,12(11):561-569,doi:10.3997/1365-2397.1994034.
Leite E P,Vidal A C.2011.3Dporosity prediction from seismic inversion and neural networks.Computers&Geosciences,37(8):1174-1180,doi:10.1016/j.cageo.2010.08.001.
Lines L R,Treitel S.1984.A review of least-squares inversion and its application to geophysical problems.Geophysical Prospecting,32(2):159-186,doi:10.1111/j.1365-2478.1984.tb00726.x.
Liu C J,Yin X Y,Wang B L.2016.Seismic stochastic inversion based on hybrid genetic algorithm.∥86th Ann.Internat Mtg.,Soc.Expi.Geophys..Expanded Abstracts,doi:10.1190/IGCBeijing2016-114.
Liu Z P,Liu J Q.1998.Seismic-controlled nonlinear extrapolation of well parameters using neural networks.Geophysics,63(6):2035-2041,doi:10.1190/1.1444496.
Manoj C,Nagarajan N.2003.The application of artificial neural networks to magnetotelluric time-series analysis.Geophysical Journal International,153(2):409-423,doi:10.1046/j.1365-246X.2003.01902.x.
Pan X P,Zhang G Z,Yin X Y.2018.Probabilistic seismic inversion for reservoir fracture and petrophysical parameters driven by rock-physics models.Chinese Journal of Geophysics(in Chinese),61(2):683-696,doi:10.6038/cjg2018K0759.
Poulton M M.2002.Neural networks as an intelligence amplification tool:A review of applications.Geophysics,67(3):979-993,doi:10.1190/1.1484539.
Robinson G.2001.Stochastic seismic inversion applied to reservoir characterization.CSEG Recorder,26(1):38-40.
Rowbotham P S,Marion D,Lamy P,et al.2003.Multidisciplinary stochastic impedance inversion:integrating geological understanding and capturing reservoir uncertainty.Petroleum Geoscience,9(4):287-294,doi:10.1144/1354-079302-490.
Sabeti H,Moradzadeh A,Ardejani F D,et al.2017.A new stochastic3Dseismic inversion using direct sequential simulation and cosimulation in a genetic algorithm framework.Journal of Mining and Environment,8(3):321-335,doi:10.22044/jme.2016.628.
Sun S M,Peng S M.2007.Inversion of geostatistics based on simulated annealing algorithm.Oil Geophysical Prospecting(in Chinese),42(1):38-43.
Tarantola A.1984.Inversion of seismic reflection data in the acoustic approximation.Geophysics,49(8):1259-1266,doi:10.1190/1.1441754.
Van Der Baan M,Jutten C.2000.Neural networks in geophysical applications.Geophysics,65(4):1032-1047,doi:10.1190/1.1444797.
Wu M,Fu L Y,Li W X.2008.A high-resolution nonlinear inversion method of reservoir parameters and its application to oil/gas exploration.Chinese Journal of Geophysics(in Chinese),51(2):546-557.
Wu S H.2010.Reservoir Characterization&Modeling(in Chinese).Beijing:Petroleum Industry Press.
Xie Y T.2007.The determination of the number of the hidden cells and the variable selection of the neural network.Statistics&Information Forum(in Chinese),22(6):9-15.
Yang X W,Zhu P M.2017.Stochastic seismic inversion based on an improved local gradual deformation method.Computers&Geosciences,109:75-86.
Zhang R,Castagna J.2011.Seismic sparse-layer reflectivity inversion using basis pursuit decomposition.Geophysics,76(6):R147-R158,doi:10.1190/geo2011-0103.1.
Zhao X F,Mendel J M.1988.Minimum-variance deconvolution using artificial neural networks.∥58th Ann.Internat Mtg.,Soc.Expi.Geophys..Expanded Abstracts,738-741,doi:10.1190/1.1892433.
潘新朋,张广智,印兴耀.2018.岩石物理驱动的储层裂缝参数与物性参数概率地震反演方法.地球物理学报,61(2):683-696,doi:10.6038/cjg2018K0759.
孙思敏,彭仕宓.2007.基于模拟退火算法的地质统计学反演方法.石油地球物理勘探,42(1):38-43.
吴媚,符力耘,李维新.2008.高分辨率非线性储层物性参数反演方法和应用.地球物理学报,51(2):546-557.
吴胜和.2010.储层表征与建模.北京:石油工业出版社.
谢远涛.2007.人工神经网络变量选取与隐藏单元数的确定.统计与信息论坛,22(6):9-15.
Cheng Q S,Chen R,Li T H.1996.Simultaneous wavelet estimation and deconvolution of reflection seismic signals.IEEE Transactions on Geoscience and Remote Sensing,34(2):377-384,doi:10.1109/36.485115.
Deutsch C V,Cockerham P W.1994.Practical considerations in the application of simulated annealing to stochastic simulation.Mathematical Geology,26(1):67-82:doi:10.1007/BF02065876.
Deutsch C V,Journel A G.1994.The application of simulated annealing to stochastic reservoir modeling.SPE Advanced Technology Series,2(2):222-227,doi:10.2118/24754-PA.
Dubrule O,Thibaut M,Lamy P,et al.1998.Geostatistical reservoir characterization constrained by 3Dseismic data.Petroleum Geoscience,4(2):121-128,doi:10.1144/petgeo.4.2.121.
Fu L Y.2004.Joint inversion of seismic data for acoustic impedance.Geophysics,69(4):994-1004,doi:10.1190/1.1778242.
Haas A,Dubrule O.1994.Geostatistical inversion-a sequential method of stochastic reservoir modelling constrained by seismic data.First Break,12(11):561-569,doi:10.3997/1365-2397.1994034.
Leite E P,Vidal A C.2011.3Dporosity prediction from seismic inversion and neural networks.Computers&Geosciences,37(8):1174-1180,doi:10.1016/j.cageo.2010.08.001.
Lines L R,Treitel S.1984.A review of least-squares inversion and its application to geophysical problems.Geophysical Prospecting,32(2):159-186,doi:10.1111/j.1365-2478.1984.tb00726.x.
Liu C J,Yin X Y,Wang B L.2016.Seismic stochastic inversion based on hybrid genetic algorithm.∥86th Ann.Internat Mtg.,Soc.Expi.Geophys..Expanded Abstracts,doi:10.1190/IGCBeijing2016-114.
Liu Z P,Liu J Q.1998.Seismic-controlled nonlinear extrapolation of well parameters using neural networks.Geophysics,63(6):2035-2041,doi:10.1190/1.1444496.
Manoj C,Nagarajan N.2003.The application of artificial neural networks to magnetotelluric time-series analysis.Geophysical Journal International,153(2):409-423,doi:10.1046/j.1365-246X.2003.01902.x.
Pan X P,Zhang G Z,Yin X Y.2018.Probabilistic seismic inversion for reservoir fracture and petrophysical parameters driven by rock-physics models.Chinese Journal of Geophysics(in Chinese),61(2):683-696,doi:10.6038/cjg2018K0759.
Poulton M M.2002.Neural networks as an intelligence amplification tool:A review of applications.Geophysics,67(3):979-993,doi:10.1190/1.1484539.
Robinson G.2001.Stochastic seismic inversion applied to reservoir characterization.CSEG Recorder,26(1):38-40.
Rowbotham P S,Marion D,Lamy P,et al.2003.Multidisciplinary stochastic impedance inversion:integrating geological understanding and capturing reservoir uncertainty.Petroleum Geoscience,9(4):287-294,doi:10.1144/1354-079302-490.
Sabeti H,Moradzadeh A,Ardejani F D,et al.2017.A new stochastic3Dseismic inversion using direct sequential simulation and cosimulation in a genetic algorithm framework.Journal of Mining and Environment,8(3):321-335,doi:10.22044/jme.2016.628.
Sun S M,Peng S M.2007.Inversion of geostatistics based on simulated annealing algorithm.Oil Geophysical Prospecting(in Chinese),42(1):38-43.
Tarantola A.1984.Inversion of seismic reflection data in the acoustic approximation.Geophysics,49(8):1259-1266,doi:10.1190/1.1441754.
Van Der Baan M,Jutten C.2000.Neural networks in geophysical applications.Geophysics,65(4):1032-1047,doi:10.1190/1.1444797.
Wu M,Fu L Y,Li W X.2008.A high-resolution nonlinear inversion method of reservoir parameters and its application to oil/gas exploration.Chinese Journal of Geophysics(in Chinese),51(2):546-557.
Wu S H.2010.Reservoir Characterization&Modeling(in Chinese).Beijing:Petroleum Industry Press.
Xie Y T.2007.The determination of the number of the hidden cells and the variable selection of the neural network.Statistics&Information Forum(in Chinese),22(6):9-15.
Yang X W,Zhu P M.2017.Stochastic seismic inversion based on an improved local gradual deformation method.Computers&Geosciences,109:75-86.
Zhang R,Castagna J.2011.Seismic sparse-layer reflectivity inversion using basis pursuit decomposition.Geophysics,76(6):R147-R158,doi:10.1190/geo2011-0103.1.
Zhao X F,Mendel J M.1988.Minimum-variance deconvolution using artificial neural networks.∥58th Ann.Internat Mtg.,Soc.Expi.Geophys..Expanded Abstracts,738-741,doi:10.1190/1.1892433.
潘新朋,张广智,印兴耀.2018.岩石物理驱动的储层裂缝参数与物性参数概率地震反演方法.地球物理学报,61(2):683-696,doi:10.6038/cjg2018K0759.
孙思敏,彭仕宓.2007.基于模拟退火算法的地质统计学反演方法.石油地球物理勘探,42(1):38-43.
吴媚,符力耘,李维新.2008.高分辨率非线性储层物性参数反演方法和应用.地球物理学报,51(2):546-557.
吴胜和.2010.储层表征与建模.北京:石油工业出版社.
谢远涛.2007.人工神经网络变量选取与隐藏单元数的确定.统计与信息论坛,22(6):9-15.