数据挖掘技术在地震属性降维中的应用
详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文
摘要
地震属性数据中包含着一些潜在的有用信息,但从地震资料中提取的地震属性多达数百种,这对实际研究造成很大困难。根据地震属性之间必然存在着相关性这一前提,对地震属性进行降维分析是解决这一困难的有效措施。将数据挖掘技术中的K-L变换和奇异值分解2种线性降维方法,分别应用到地震属性降维中,再将降维后的地震属性应用到研究区的实际地震数据中进行测试,结果发现降维后的地震属性均集中在特征值最大的那个新属性上。并依次减小,认为用降维后的地震属性预测储层比用单一地震属性更符合地质规律。
Several hundreds of seismic attributes from seismic data make it difficult to apply in practice although the seismic attributes contain much potential useful information.Based on the interdependeney of the seismic attributes,the reduction of dimensions of seismic attributes is a valid method to resolve this problem.Here we use the K-L transformation and SVD methods in the reduction of dimensions of seismic attributes.The test of practical data indicates that the main features in the seismic attributes are distributed in the first main component after dimension reduction,and decrease successively.It is better to predict reservoirs by using the seismic attributes reduced dimensions than single seismic attribute.
引文
[1]Wang Wei,Ma Qinzhong,Wu Gengfeng,et al.Primary com-ponent analysis method and reduction of seismicity parameters[J].Acta Seismologica Sinica,2005,27(5):524-531.[王炜,马钦忠,吴耿锋,等.主成分分析及地震活动参数的约减[J].地震学报,2005,27(5):524-531.]
    [2]Wang Wei,Lin Mingzhou,Ma Qinzhong,et al.The data min-ing and its prospect of application in earthquake forecast[J].Recent Developments in World Seismology,2005,(12):1-13.[王炜,林命週,马钦忠,等.数据挖掘及其在地震预报中的应用前景[J].国际地震动态,2005,(12):1-13.]
    [3]Huang Yunfeng,Yang Zhanlong,Guo Jingyi,et al.Seismic at-tribute analysis and application in subtle traps exlporaation[J].Natural Gas Geoscience,2006,17(5):739-742.[黄云峰,杨占龙,郭精义,等.地震属性分析及其在岩性油气藏勘探中的应用[J].天然气地球科学,2006,17(5):739-742.]
    [4]Zhang Lihua,Pan Baozhi,Shan Gangyi,et al.Linear dimen-sion-reducing mapping method to identify the lithology of vol-canic rocks[J].Computing Techniques for Geophysical andGeochemical Exploration,2007,29(2):112-114.[张丽华,潘保芝,单刚义,等.线性降维映射方法识别火山岩岩性[J].物探化探计算技术,2007,29(2):112-114.]
    [5]Seung H S,D D Lee.The manifold ways of perception[J].Sci-ence,2000,290(5500):2268-2269.
    [6]Tenenbaum J B,Silvo J C,Langford J C.A global geoetricframework for nonlinear dimensionality reduction[J].Sci-ence,2000,290(5500):2319-2323.
    [7]Roweis S T,Saul L K.Nonlinear dimensionality reduction bylocally linear embedding[J].Science,2000,290(5500):2323-2326.
    [8]Freire S L M,Ulrych T J.Application of singular value de-composition to vertical seismic profiling[J].Geophysics,1988,53(6):778-785.
    [9]Li Zaiguang,Yang Zhanlong,Liu Juntian,et al.Hydrocarbondetection by integrating multiple attributes[J].Natural GasGeoscience,2006,17(5):727-730.[李在光,杨占龙,刘俊田,等.多属性综合方法预测含油气性及其效果[J].天然气地球科学,2006,17(5):727-730.]
    [10]Liang Yixiong.Research on Subspace Analysis-Based FeatureExtraction and Face Recognition[D].Chongqing:ChongqingUniversity,2005.[梁毅雄.基于子空间分析的人脸特征提取及识别研究[D].重庆:重庆大学,2005.]
    [11]Liu Xiaoming.Research of Mmainfold Learning in Data Di-mension Reduction and Classification[D].Zhejiang:ZhejiangUniversity,2007.[刘小明.数据降维及分类中的流行学习研究[D].浙江:浙江大学,2007.]
    [12]Yu Xiaosheng,Zhou Ning.Research on methods of dimension-ality reduction in high-dimensional data[J].Information Sci-ence,2007,25(8):1248-1251.[余肖生,周宁.高维数据降维方法研究[J].情报科学,2007,25(8):1248-1251.]
    [13]Liu Weifang,Yu Xinghe,He Qiongying.Application of seis-mic attributes in SU gas field development[J].Natural GasGeoscience,2006,17(6):862-867.[刘伟方,于兴河,何琼英.地震属性在SU气田开发中的应用[J].天然气地球科学,2006,17(6):862-867.]

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