地震相约束的多属性储层预测方法研究
摘要
多元线性回归与神经网络的组合已被广泛应用于多属性储层预测,但在神经网络训练时,对已知井数目总是存在很大的依赖性,而在勘探初期往往钻井数据又很少。为解决这一问题,提出可以从现有的地震属性数据中,挖掘出更多的有效信息来弥补测井参数的缺乏。即首先利用模糊自组织神经网络将一组地震属性进行聚类映射,反映出不同沉积环境下不同地震响应的特征区域,即地震相;然后结合地质和开发资料,对地震相进行解释,并用地震相的信息约束储层预测。地震相约束可以从两方面进行,一是增加新的、合理的虚拟井参数,二是将地震聚类数据作为新的输入属性。按此思路对模糊自组织聚类、多元线性回归和径向基函数网络进行了组合,通过数学推导证明了该流程的可行性。实际资料处理、解释表明,无论时移监测中的压力差预测,还是勘探初期储层的含油饱和度预测,该流程都能获得理想的效果。
Integrated multiple linear regression and radial basis function neural network is an effective quantitative approach in reservoir prediction with seismic multiattribute,but the effect of neural network depend on number of the wells used.Generally,a few wells have been drilled in the preliminary stage of exploration,and the lack of training samples leads to failure of the pattern recognition.To solve this problem,more geological information should be found to make up for the lack of well parameters based on attributes.Fuzzy self-organizing neural network is able to cluster a set of seismic attributes.The mapping reflects the different seismic response of sedimentary environments under the different regions,which is called seismic facies.Combination of geology and development data,seismic facies was interpreted.Then,information of seismic facies as constraint was added in reservoir prediction by two ways.One is that reasonable imaginary wells parameters should be added,and the second way is that clustering data will be an extra input attribute.in this way,the paper integrates fuzzy self-organizing cluster,multiple linear regression and radial basis function.The process is feasible by mathematical deducing.Meanwhile,in practical applications such as the pressure difference monitoring and the oil saturation estimation,the approach works well.
Integrated multiple linear regression and radial basis function neural network is an effective quantitative approach in reservoir prediction with seismic multiattribute,but the effect of neural network depend on number of the wells used.Generally,a few wells have been drilled in the preliminary stage of exploration,and the lack of training samples leads to failure of the pattern recognition.To solve this problem,more geological information should be found to make up for the lack of well parameters based on attributes.Fuzzy self-organizing neural network is able to cluster a set of seismic attributes.The mapping reflects the different seismic response of sedimentary environments under the different regions,which is called seismic facies.Combination of geology and development data,seismic facies was interpreted.Then,information of seismic facies as constraint was added in reservoir prediction by two ways.One is that reasonable imaginary wells parameters should be added,and the second way is that clustering data will be an extra input attribute.in this way,the paper integrates fuzzy self-organizing cluster,multiple linear regression and radial basis function.The process is feasible by mathematical deducing.Meanwhile,in practical applications such as the pressure difference monitoring and the oil saturation estimation,the approach works well.
引文
[1]Ronen S,Schultz P S,Hattori M,et al.Seismic-guided es-timation of log properties.Part2:Using artificial neural networks for nonlinear attribute calibration[J].The Lead-ing Edge,1994,13(6):674-678.
[2]Arthur E B,Yu-Chi Ho.Applied optimal control:optimi-zation,estimation,and control[M].New York:John Wiley&Sons Inc,1979.
[3]Masters T.Signal and image processing with neural net-works[M].New York:John Wiley&Sons Inc,1994.
[4]Masters T.Advanced algorithms for neural networks[M].New York:John Wiley&Sons Inc,1995.
[5]Moody J,Darken C.Fast learning in networks of locally-tuned processing units[J].Neural Computation,1989,1(2):281-294.
[6]Specht D F.Probabilistic neural networks[J].Neural Net-works,1990,3(1):109-118.
[7]Specht D F.A general regression neural network[J].IEEE Transactions on Neural Network,1991,2(6):568-576.
[8]Hopfield J J.Neural networks and physical systems with emergent collective computational abilities[J].Proceed-ings of the National Academy of Sciences USA,1982,79(8):2554-2558.
[9]Caianiello E R.Outline of a theory of thought-processes and thinking machines[J].Journal of Theoretical Biology,1961,1(2):204-235.
[10]Liu,Z,Liu J.Seismic controlled nonlinear extrapolation of well parameters using neural networks[J].Geophysics,1998,63(6):2035-2041.
[11]Tonn R.Neural network seismic reservoir characteriza-tion in a heavy oil reservoir[J].The Leading Edge,2002,21(3):309-312.
[12]Russell B H,Hampson D P,Lines L R.Application of the radial basis function neural network to the prediction of log properties from seismic attributes—A channel sand case study[C].73rd Annual International Meeting,SEG,Expanded Abstracts,2003:454-457.
[13]Pramanik A G,Singh V,V Rajiv,et al.Estimation of ef-fective porosity using geostatistics and multiattribute transforms:A case study[J].Geophysics,2004,69(2):352-372.
[14]Tebo J M,Hart B S.Use of volume-based3D seismic at-tribute analysis to characterize physical-property distri-bution:a case study to delineate sedimentologic heteroge-neity at the Appleton field,Southwestern Alabama,U.S.A[J].Journal of Sedimentary Research,2005,75(4):723-73.
[15]孟召平,郭彦省,王赟,等.基于地震属性的煤层厚度预测模型及其应用[J].地球物理学报,2006,49(2):512-517.
[16]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.
[17]Carmen C D,Fred M,Rodney C.Exploration of Lower Cretaceous sands in the Leland Area,Alberta,using seis-mically derived rock properties[J].First Break,2009,27(11):53-60.
[18]Farzadi P.Seismic facies analysis based on3D multi-at-tribute volume classification,Dariyan Formation,SE Per-sian Gulf[J].Journal of Petroleum Geology,2006,29(2):159-173.
[19]丁峰,尹成,朱振宇,等.利用改进的自组织网络进行地震属性分析[J].西南石油大学学报:自然科学版,2009,31(4):47-51.
[20]Mehdi E.Extrapolation of log properties by integrating fuzzy-self organizing maps and local linear modeling[J].79th Annual International Meeting,SEG,Expanded Abstracts,2009:1915-1919.
[21]Kohonen T.Self-organization and associative memory(3rd Edition)[J].New York:Springer-Verlag,1989.
[22]Bezdek J C,Tsao E C-K,Pal N R.Fuzzy Kohonen clus-tering networks[C].IEEE International Conference on Computational Intelligence,1992:1035-1043.
[23]沈涛,甘骏人,姚林声.模糊人工神经网络方法在电路划分问题中的应用[J].计算机学报,1992,15(9):641-647.
[24]Hu W,Xie D,Tan T,et al.Learning activity patterns using fuzzy self-organizing neural network[J].IEEE Transactions on Systems,Man,and Cybernetics,2004,34(3):1618-1626.
[25]Wong M,Lane T.A kth nearest neighbor clustering pro-cedure[J].Journal of the Royal Statistical Society Series B,1983,45(3):362-368.
[26]Schultz P S,Ronen S,Hattori M,et al.Seismic-guided esti-mation of log properties.Part1:A data-driven interpretation methodology[J].The Leading Edge,1994,13(6):305-311.
[27]古发明,尹成,丁峰.应用粗集理论优选地震属性的方法研究[J].西南石油大学学报,2007,29(S1):1-4.
[2]Arthur E B,Yu-Chi Ho.Applied optimal control:optimi-zation,estimation,and control[M].New York:John Wiley&Sons Inc,1979.
[3]Masters T.Signal and image processing with neural net-works[M].New York:John Wiley&Sons Inc,1994.
[4]Masters T.Advanced algorithms for neural networks[M].New York:John Wiley&Sons Inc,1995.
[5]Moody J,Darken C.Fast learning in networks of locally-tuned processing units[J].Neural Computation,1989,1(2):281-294.
[6]Specht D F.Probabilistic neural networks[J].Neural Net-works,1990,3(1):109-118.
[7]Specht D F.A general regression neural network[J].IEEE Transactions on Neural Network,1991,2(6):568-576.
[8]Hopfield J J.Neural networks and physical systems with emergent collective computational abilities[J].Proceed-ings of the National Academy of Sciences USA,1982,79(8):2554-2558.
[9]Caianiello E R.Outline of a theory of thought-processes and thinking machines[J].Journal of Theoretical Biology,1961,1(2):204-235.
[10]Liu,Z,Liu J.Seismic controlled nonlinear extrapolation of well parameters using neural networks[J].Geophysics,1998,63(6):2035-2041.
[11]Tonn R.Neural network seismic reservoir characteriza-tion in a heavy oil reservoir[J].The Leading Edge,2002,21(3):309-312.
[12]Russell B H,Hampson D P,Lines L R.Application of the radial basis function neural network to the prediction of log properties from seismic attributes—A channel sand case study[C].73rd Annual International Meeting,SEG,Expanded Abstracts,2003:454-457.
[13]Pramanik A G,Singh V,V Rajiv,et al.Estimation of ef-fective porosity using geostatistics and multiattribute transforms:A case study[J].Geophysics,2004,69(2):352-372.
[14]Tebo J M,Hart B S.Use of volume-based3D seismic at-tribute analysis to characterize physical-property distri-bution:a case study to delineate sedimentologic heteroge-neity at the Appleton field,Southwestern Alabama,U.S.A[J].Journal of Sedimentary Research,2005,75(4):723-73.
[15]孟召平,郭彦省,王赟,等.基于地震属性的煤层厚度预测模型及其应用[J].地球物理学报,2006,49(2):512-517.
[16]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.
[17]Carmen C D,Fred M,Rodney C.Exploration of Lower Cretaceous sands in the Leland Area,Alberta,using seis-mically derived rock properties[J].First Break,2009,27(11):53-60.
[18]Farzadi P.Seismic facies analysis based on3D multi-at-tribute volume classification,Dariyan Formation,SE Per-sian Gulf[J].Journal of Petroleum Geology,2006,29(2):159-173.
[19]丁峰,尹成,朱振宇,等.利用改进的自组织网络进行地震属性分析[J].西南石油大学学报:自然科学版,2009,31(4):47-51.
[20]Mehdi E.Extrapolation of log properties by integrating fuzzy-self organizing maps and local linear modeling[J].79th Annual International Meeting,SEG,Expanded Abstracts,2009:1915-1919.
[21]Kohonen T.Self-organization and associative memory(3rd Edition)[J].New York:Springer-Verlag,1989.
[22]Bezdek J C,Tsao E C-K,Pal N R.Fuzzy Kohonen clus-tering networks[C].IEEE International Conference on Computational Intelligence,1992:1035-1043.
[23]沈涛,甘骏人,姚林声.模糊人工神经网络方法在电路划分问题中的应用[J].计算机学报,1992,15(9):641-647.
[24]Hu W,Xie D,Tan T,et al.Learning activity patterns using fuzzy self-organizing neural network[J].IEEE Transactions on Systems,Man,and Cybernetics,2004,34(3):1618-1626.
[25]Wong M,Lane T.A kth nearest neighbor clustering pro-cedure[J].Journal of the Royal Statistical Society Series B,1983,45(3):362-368.
[26]Schultz P S,Ronen S,Hattori M,et al.Seismic-guided esti-mation of log properties.Part1:A data-driven interpretation methodology[J].The Leading Edge,1994,13(6):305-311.
[27]古发明,尹成,丁峰.应用粗集理论优选地震属性的方法研究[J].西南石油大学学报,2007,29(S1):1-4.
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