支持向量机模型在火山岩储层预测中的应用——以徐家围子断陷徐东斜坡带为例
|
摘要
火山岩储层的发育程度是控制徐家围子断陷火山岩气藏的重要因素,但火山岩储层以岩性复杂、横向变化快、井问可对比性差为特点,火山岩储层的准确识别、厚度的精确描述是火山岩气藏勘探开发的难题.针对这一难题,作者提出在专家优化地震属性组合的基础上确定支持向量机模型,进而预测火山岩储层厚度.该技术在实际应用中取得了良好效果,预测的火山岩储层厚度符合研究区的地质规律,预测结果能够保持地震属性的横向分辨率和整体变化趋势,在井点处吻合程度较高,为火山岩储层预测提供了新的思路.
In Xujiaweizi depression of northern Songliao Basin,the development of volcanic reservoir dominated largely gas accumulation.However,an accurate description for volcanic distribution is always difficult for geologists,because of its complex lithology,lateral heterogeneity and poor comparison between wells.With regard to this problem,we present the model of support vector machine as a solution.By the analyses of the combination of seismic attributes,this model can be used to indicate volcanic reservoir.The thickness of volcanic rocks and its distribution,which are predicted through using this method,can reflect its sedimentation model and maintain the lateral resolution of seismic as well as the overall trend.In addition,the thickness of volcanic rocks at drilled wells is highly consistent with those of well logs.
In Xujiaweizi depression of northern Songliao Basin,the development of volcanic reservoir dominated largely gas accumulation.However,an accurate description for volcanic distribution is always difficult for geologists,because of its complex lithology,lateral heterogeneity and poor comparison between wells.With regard to this problem,we present the model of support vector machine as a solution.By the analyses of the combination of seismic attributes,this model can be used to indicate volcanic reservoir.The thickness of volcanic rocks and its distribution,which are predicted through using this method,can reflect its sedimentation model and maintain the lateral resolution of seismic as well as the overall trend.In addition,the thickness of volcanic rocks at drilled wells is highly consistent with those of well logs.
引文
[1] 任延广,朱德丰,万传彪等.松辽盆地徐家围子断陷天然气聚集规律与下步勘探方向.大庆石油地质与开发,2004,23(5) :26～29 Ren Y G,Zhu D F,Wan C B,et al.Natural gas accumulation rule of Xujiaweizi Depression in Songliao Basin and future exploration target.Petroleum Geology & Oilfield Development in Daqing(in Chinese),2004,23(5) :26～29
[2] 冯志强.松辽盆地庆深大型气田的勘探前景.天然气工业,2006,26(6) :1～5 Feng Z Q.Exploration potential of large Qingshen gas field in the Songliao basin.Natural Gas Industry (in Chinese),2006,26(6) :1～5
[3] 张元高,陈树民,张尔华等.徐家围子断陷构造地质特征研究新进展.岩石学报,2010,26(1) :142～148 Zhang Y G,Chen S M,Zhang E H,et al.The new progress of Xujiaweizi Fault Depression characteristics of structural geology research.Acta Petrologica Sinica (in Chinese),2010,26(1) :142～148
[4] 张尔华,姜传金,张元高等.徐家围子断陷深层结构形成与演化的探讨.岩石学报,2010,26(1) :149～157 Zhang E H,Jiang C J,Zhang Y G,et al.Study on the formation and evolution of deep structure of Xujiaweizi fault depression.Acta Petrologica Sinica (in Chinese),2010,26(1) :149～157
[5] 姜传金,陈树民,初丽兰等.徐家围子断陷营城组火山岩分布特征及火山喷发机制的新认识.岩石学报,2010,26(1) :63～72 Jiang C J,Chen S M,Chu L L,et al.A new understanding about the volcanic distribution characteristics and eruption mechanism of Yingchen formation in Xujiaweizi fault depression.Acta Petrologica Sinica (in Chinese),2010,26(1) :63～72
[6] Zhang E H,Li A,Song Y Z.Seismic recognition method of channel sand body of Fuyang pay Zone in Songliao Basin:Nonmarine seismic sedimentology interpretation approach.CPS/SEG Beijing 2009 International Geophysical Conference & Exposition.Id:1023
[7] 乐友喜,王永刚.由地震属性向储层参数转化的综合效果分析.石油物探,2002,41(2) :202～206 Le Y X,Wang Y G.A comprehensive effect analysis of conversion from seismic attributes to reservoir parameters.Geophysical Prospecting for Petroleum (in Chinese),2002,41(2) :202～206
[8] 周宗良,肖建玲,张枫.地震属性的优化处理及储层厚度的 定量解释.新疆地质,2002,20(3) :262～265 Zhou Z L,Xiao J L,Zhang F.Optimized processing of seismic attributes and quantitative interpretation of reservoir thickness.Xinjiang Geology (in Chinese),2002,20(3) :262～265
[9] 张彦周,刘叶玲,谢宝英.支持向量机在储层厚度预测中的应用.勘探地球物理进展.2005,28(6) :422～424 Zhang Y Z,Liu Y L.Xie B Y.Application of SVM in prediction of reservoir thickness.Progress in Exploration Geophysics(in Chinese).2005,28(6) :422～424
[10] 文政,高松洋,毕广武.支持向量机在复杂岩性测井识别中的应用.大庆石油地质与开发,2009,28(1) :134～137 Wen Z,Gao S Y,Bi G W.Application of support vector machine (SVM) in complex lithology identification by well logging.Petroleum Geology & Oilfield Development in Daqing(in Chinese),2009,28(1) :134～137
[11] 杨培杰.(?)兴耀.基于支持向量机的叠前地震反演方法.中国石油(?)报(自然科学版),2008,32(1) :37～41 (?)Yin X Y.Prestack seismic inversion method based (?)vector machine.Journal of China University of (?).2008,32(1) :37～41
[12] (?).谭明友.基于支持向量机的地震储层参数预测方法初探.油气地球物理,2008,6(1) :34～37 Zhu J B,Tan M Y.Seismic reservoir parameters prediction via support vector machine.Petroleum Geophysics,2008,6(1) :34～37
[13] Kappler K,Kuzma H A,Rector J W.A comparison of stand inversion,neural networks and support vector machines.75~(th) Annual International Meeting SEG,Expanded Abstracts,2005． 1725～1727
[14] Burges C.A tutorial on support vector machines for pattern recognition.Data Mining and Knowledge Discovery,1998,2(2) :121～167
[15] 朱国强,刘士荣,俞金寿.支持向量机及其在函数逼近中的应用.华东理工大学学报,2002,28(5) :555～559 Zhu G Q,Liu S R,Yu J S.Support vector machine and its applications to function approximation.Journal of East China University of Science and Technology (in Chinese),2002,28(5) :555～559
[16] 乐友喜,袁全社.支持向量机方法在储层预测中的应用,石油物探,2005,44(4) :388～392 Le Y S,Yuan Q S.Application of SVM method in reservoir prediction.Geophysical Prospecting for Petroleum (in Chinese),2005,44(4) :388～392
[17] Vapnik V.The Nature of Statistical Learning Theory.New York,Spring-Verlag,1995． 314
[18] Vapnik V,Golowich S,Smola A.Support vector method for function approximation,regression estimation,and signal processing.Advances in Neural Information Processing Systems,1996． 281～287
[19] Cherkassky V,Mulier F.Vapnik-Chervonenkis (VC) learning theory and its applications.IEEE Transactions on Neural Netwoks,1999,10(5) :985～987
[2] 冯志强.松辽盆地庆深大型气田的勘探前景.天然气工业,2006,26(6) :1～5 Feng Z Q.Exploration potential of large Qingshen gas field in the Songliao basin.Natural Gas Industry (in Chinese),2006,26(6) :1～5
[3] 张元高,陈树民,张尔华等.徐家围子断陷构造地质特征研究新进展.岩石学报,2010,26(1) :142～148 Zhang Y G,Chen S M,Zhang E H,et al.The new progress of Xujiaweizi Fault Depression characteristics of structural geology research.Acta Petrologica Sinica (in Chinese),2010,26(1) :142～148
[4] 张尔华,姜传金,张元高等.徐家围子断陷深层结构形成与演化的探讨.岩石学报,2010,26(1) :149～157 Zhang E H,Jiang C J,Zhang Y G,et al.Study on the formation and evolution of deep structure of Xujiaweizi fault depression.Acta Petrologica Sinica (in Chinese),2010,26(1) :149～157
[5] 姜传金,陈树民,初丽兰等.徐家围子断陷营城组火山岩分布特征及火山喷发机制的新认识.岩石学报,2010,26(1) :63～72 Jiang C J,Chen S M,Chu L L,et al.A new understanding about the volcanic distribution characteristics and eruption mechanism of Yingchen formation in Xujiaweizi fault depression.Acta Petrologica Sinica (in Chinese),2010,26(1) :63～72
[6] Zhang E H,Li A,Song Y Z.Seismic recognition method of channel sand body of Fuyang pay Zone in Songliao Basin:Nonmarine seismic sedimentology interpretation approach.CPS/SEG Beijing 2009 International Geophysical Conference & Exposition.Id:1023
[7] 乐友喜,王永刚.由地震属性向储层参数转化的综合效果分析.石油物探,2002,41(2) :202～206 Le Y X,Wang Y G.A comprehensive effect analysis of conversion from seismic attributes to reservoir parameters.Geophysical Prospecting for Petroleum (in Chinese),2002,41(2) :202～206
[8] 周宗良,肖建玲,张枫.地震属性的优化处理及储层厚度的 定量解释.新疆地质,2002,20(3) :262～265 Zhou Z L,Xiao J L,Zhang F.Optimized processing of seismic attributes and quantitative interpretation of reservoir thickness.Xinjiang Geology (in Chinese),2002,20(3) :262～265
[9] 张彦周,刘叶玲,谢宝英.支持向量机在储层厚度预测中的应用.勘探地球物理进展.2005,28(6) :422～424 Zhang Y Z,Liu Y L.Xie B Y.Application of SVM in prediction of reservoir thickness.Progress in Exploration Geophysics(in Chinese).2005,28(6) :422～424
[10] 文政,高松洋,毕广武.支持向量机在复杂岩性测井识别中的应用.大庆石油地质与开发,2009,28(1) :134～137 Wen Z,Gao S Y,Bi G W.Application of support vector machine (SVM) in complex lithology identification by well logging.Petroleum Geology & Oilfield Development in Daqing(in Chinese),2009,28(1) :134～137
[11] 杨培杰.(?)兴耀.基于支持向量机的叠前地震反演方法.中国石油(?)报(自然科学版),2008,32(1) :37～41 (?)Yin X Y.Prestack seismic inversion method based (?)vector machine.Journal of China University of (?).2008,32(1) :37～41
[12] (?).谭明友.基于支持向量机的地震储层参数预测方法初探.油气地球物理,2008,6(1) :34～37 Zhu J B,Tan M Y.Seismic reservoir parameters prediction via support vector machine.Petroleum Geophysics,2008,6(1) :34～37
[13] Kappler K,Kuzma H A,Rector J W.A comparison of stand inversion,neural networks and support vector machines.75~(th) Annual International Meeting SEG,Expanded Abstracts,2005． 1725～1727
[14] Burges C.A tutorial on support vector machines for pattern recognition.Data Mining and Knowledge Discovery,1998,2(2) :121～167
[15] 朱国强,刘士荣,俞金寿.支持向量机及其在函数逼近中的应用.华东理工大学学报,2002,28(5) :555～559 Zhu G Q,Liu S R,Yu J S.Support vector machine and its applications to function approximation.Journal of East China University of Science and Technology (in Chinese),2002,28(5) :555～559
[16] 乐友喜,袁全社.支持向量机方法在储层预测中的应用,石油物探,2005,44(4) :388～392 Le Y S,Yuan Q S.Application of SVM method in reservoir prediction.Geophysical Prospecting for Petroleum (in Chinese),2005,44(4) :388～392
[17] Vapnik V.The Nature of Statistical Learning Theory.New York,Spring-Verlag,1995． 314
[18] Vapnik V,Golowich S,Smola A.Support vector method for function approximation,regression estimation,and signal processing.Advances in Neural Information Processing Systems,1996． 281～287
[19] Cherkassky V,Mulier F.Vapnik-Chervonenkis (VC) learning theory and its applications.IEEE Transactions on Neural Netwoks,1999,10(5) :985～987
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