基于神经网络的井间地震数据外推及多尺度反演
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
多尺度地震资料联合反演将地面地震、井间地震和VSP等资料有机结合在一起,充分利用了不同地震资料的优点,达到了提高反演分辨率的目的。但受观测系统的限制,井间地震获得的只是一段二维剖面的信息,而地面地震是地下三维数据体的综合响应,因此无法对整个工区进行联合反演。针对这一问题,基于地层对地震波吸收的非线性系统理论,提出了利用神经网络建立地面地震数据和井间地震资料映射关系的方法。由于神经网络具有层状结构且输入、输出之间的映射关系是非线性的,从而建立地面地震数据与已有的井间地震数据之间的非线性理论模型,再将此映射关系应用到整个工区,得到高分辨率的井间地震。然后利用模型测试研究了该方法的可行性和鲁棒性。最后,将该方法应用到实际地震资料中,所得的多尺度反演结果分辨率明显提高,证明了该方法的可靠性及适应性。
The multi-scale seismic joint inversion method,which integrates the cross- well seismic data,VSP data and other seismic data with the surface seismic data organically,is fully developed the advantages of different seismic data to achieve the purpose of improving the inversion resolution.However,restricted by the observing system,the cross-well seismic data only reflects the information of a 2-D profile.The surface seismic data is the response of the three-dimensional data volume.So the joint inversion is not carried out in the whole workspace.Considering this problem,we propose a method to build the mapping relationship between the cross- well data and the surface seismic data using the neural networks based on the nonlinear system theory of the formation absorption of seismic waves.The neural network has a layered structure and the mapping relationship between the input and output is nonlinear which can describe the complex nonlinear theory model between the surface seismic data and the cross-well seismic data.Then we apply the mapping relationship to the whole workspace and obtain the cross-well seismic data with high resolution.The numerical tests show that the proposed method is feasible and noise resistent.Finally,we apply the proposed method to the field data,and the corresponding resolution of the multi-scale seismic joint inversion result is highly improved,which demonstrates the reliability and adaptability of the proposed method.
引文
[1]张汝杰,贺振华,王理.井间地震高斯射线束正演方法[J].物探化探计算技术,1997,19(2):128-137.ZHANG R J,HE ZH H,WANG L.Forward modeling by Gaussian beam method in crosswell seismic[J].Computing techniques for geophysical and geochemical exploration,1997,19(2):128-137.(In Chinese)
    [2]施振飞,印兴耀.利用井间地震资料与测井资料进行储层精细解释[J].石油地球物理勘探,2005,40(2):172-175.SHI Z F,YIN X Y.Using cross-hole seismic data and logging data for fine reservoir interpretation[J].Oil geophysical prospecting,2005,40(2):172-175.(In Chinese)
    [3]杨孛,李瑞,杨滔.白马庙须家河薄互层储层预测方法与应用[J].物探化探计算技术,2012,34(6):685-690.YANG B,LI R,YANG T.Xujiahe thin interbedded reservoir prediction methods and applications in Baimamiao[J].Computing techniques for geophysical and geochemical exploration,2012,34(6):685-690.(In Chinese)
    [4]杨邦伟,谭茂金,陈莹.用成像测井资料描述碳酸盐岩储集层——以车古20潜山为例[J].物探化探计算技术,2007,29(3):234-238.YANG B W,TAN M J,CHEN Y.Description of Chegu 20 buried-hill reservoir in futai field with imaging well logging data[J].Computing techniques for geophysical and geochemical exploration,2007,29(3):234-238.(In Chinese)
    [5]曹丹平,印兴耀,张繁昌,等.多尺度地震资料联合反演方法研究[J].地球物理学报,2009(4):1059-1067.CAO D P,YIN X Y,ZHANG F C,et al.A study on the method of joint inversion of multiscale data[J].Chinese Journal of Geophysics,2009(4):1059-1067.(In Chinese)
    [6]徐雷,迟惠生.静态前馈型网络的监督学习方法研究进展[J].电子学报,1992,20(10):106-113.XU L,CHI H S.Research advances on supervised learning ol static feedforward networks[J].Acta Electronica Sinica,1992,20(10):106-113.(In Chinese)
    [7]席道瑛,张涛.BP网络的改进及模拟退火神经网络在地学中应用[J].物探化探计算技术,1996,18(3):219-224.XI D Y,ZHANG T.An improvement on BP neural network and the application of the theory of simulated annealing to geosciences[J].Computing techniques for geophysical and geochemical exploration,1996,18(3):219-224.(In Chinese)
    [8]张繁昌,印兴耀,吴国忱,等.用模拟退火神经网络技术进行波阻抗反演[J].石油大学学报:自然科学版,1997,21(6):16-18.ZHANG F C,YIN X Y,WU G CH,et al.Impedance inversion by using annealing neural network[J].Journal of the University of Petroleum,1997,21(6):16-18.(In Chinese)
    [9]QIAO H,PENG J,XU Z B,et al.A reference model approach to stability analysis of neural networks[J].Systems,Man,and Cybernetics,Part B:Cybernetics,IEEE Transactions on,2003,33(6):925-936.
    [10]邱颖,孟庆武,李梯,等.神经网络用于岩性及岩相预测的可行性分析[J].地球物理学进展,2001,16(3):76-84.QIU Y,MENG Q W,LI T,et al.The feasibility analysis of neural network in the prediction of lithology and lithofacles[J].Progress in Geophysics,2001,16(3):76-84.(In Chinese)
    [11]张宏兵,杨长春.正则参数控制下的波阻抗约束反演[J].地球物理学报,2004,46(6):827-834.ZHANG H B,YANG CH CH.A constrained impedance inversion method controlled by regularized parameters[J].Chinese Journal of Geophysics,2004,46(6):827-834.(In Chinese)
    [12]周家斌,王允宽,杨桂英.关于预测误差平方和最小准则的几点看法[J].数理统计与管理,1996,15(3):43-46.ZHOU J B,WANG Y K,YANG G Y.A note on The stepwise algorithm for selecting predictors on the basis of the criterion from prediction sum of squares[J].Journal of Applied Statistics and Management,1996,15(3):43-46.(In Chinese)
    [13]王金峰,罗省贤.BP神经网络的改进及其在初至波拾取中的应用[J].物探化探计算技术,2006,28(1):14-17.WANG J F,LUO SH X.The improved BP neural network and its application in seismic first breaks picking[J].Computing techniques for geophysical and geochemical exploration,2006,28(1):14-17.(In Chinese)
    [14]宫健,刘浩杰.利用井间地震提高地面地震资料分辨率[J].石油地球物理勘探,2009,44(4):451-456.GONG J,LIU H J.Using cross-hole seismic data to improve resolution of surface-seismic data[J].Oil geophysical prospecting,2009,44(4):451-456.(In Chinese)
    [15]曹丹平,印兴耀,张繁昌,等.井间地震约束下的高分辨率波阻抗反演方法研究[J].石油物探,2010,49(5):425-429.CAO D P,YIN X Y,ZHANG F C,et al.Study of high-resolution impedance inversion method constrained by crosswell seismic data[J].Geophysical Prospecting for Petroleum,2010,49(5):425-429.(In Chinese)
    [16]ROBINSON EA.Predictive decomposition of time series with application to seismic exploration[J].Geophysics,1967,32(3):418-484.
    [17]ROBINSON EA.Predictive decomposition of seismic traces[J].Geophysics,1957,22(4):767-778.
    [18]张繁昌,李传辉,吴国忱,等.地层吸收对弹性参数的影响和叠前QAVO反演[J].物探化探计算技术,2010,32(3):232-240.ZHANG F C,LI CH H,WU G CH,et al.The effect of rock absorption on elastic parameters and pre-stack QAVO inversion[J].Computing techniques for geophysical and geochemical exploration,2010,32(3):232-240.(In Chinese)
    [19]尹陈,贺振华,黄德济.基于二维粘滞性波动方程的地震波衰减理论研究[J].物探化探计算技术,2008,30(5):353-356.YIN CH,HE ZH H,HUANG D J.The research and the application of the seismic attenuation theory based on the wave equation[J].Computing techniques for geophysical and geochemical exploration,2008,30(5):353-356.(In Chinese)
    [20]DASGUPTA R,CLARK R A.Estimation of Q from surface seismic reflection data[J].Geophysics,1998,63(6):2120-2128.
    [21]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 M,FU L Y,LI W X.A high-resolution nonlinear inversion method of reservoir parameters and its application to oil/gas exploration[J].Chinese Journal of Geophysics,2008,51(2):546-557.(In Chinese)

版权所有:© 2023 中国地质图书馆 中国地质调查局地学文献中心