基于改进有监督局部线性嵌入的地震属性降维优化

英文篇名：Reducing Dimension and Optimization of Seismic Attribute Based on Developed SLLE
中文刊名：国土资源科技管理
英文刊名：Scientific and Technological Management of Land and Resources
作者：胡丹 ; 薛源
英文作者：HU Dan1 ; XUE Yuan2 ; 3(1.College of Tourism and Urban-Rural Planning ; Chengdu University of Technology ; Chengdu 610059 ; China ; 2.Geomathematics Key Laboratory of Sichuan Province ; Chengdu 610059 ; China ; 3.State Key Laboratory of Geological Hazard Prevention and Geological Environment Protection ; Chengdu University of Technology ; Chengdu 610059 ; China)
中文关键词：地震属性 ; 降维优化 ; 有监督局部线性嵌入 ; 模糊聚类
英文关键词：seismic attribute ; reduce dimension ; supervised local linear embedding ; fuzzy cluster
出版日期：2012-12-15
机构：成都理工大学旅游与城乡规划学院;成都理工大学数学地质四川省重点实验室;成都理工大学地质灾害防治与地质环境保护国家重点实验室;
年：2012
期：06
出版单位：国土资源科技管理

摘要

为克服直接从地震资料中获取的地震属性具有维数高、数据量大、信息冗余、高度非线性,且数据样本缺乏先验知识分类等缺陷,用基于等价关系的模糊聚类方法对有监督局部线性嵌入算法进行改进,将其应用于地震属性的非线性降维优化,实例表明其地震属性降维优化效果优于常规线性降维方法,为地震资料解释处理、储层预测及物性参数反演提供了良好可靠的数据资料。
In order to overcome the defects of the seismic attribute which is extracted directly from seismic data,such as high dimension,enormous data,redundant information,high nonlinearity and sample data's lack of priori knowledge classification,the fuzzy cluster method based on equivalence relation is used to supervise local linear embedding.The cases of study indicate that the result of nonlinear reducing dimension and optimization of seismic attribute based on the developed SLLE is better than that of the other conventional linear reduce dimension methods.The algorithm can provide good and reliable data for seismic data interpretation,reservoir prediction and material parameters inversion.

引文

[1]印兴耀,周静毅.地震属性优化方法综述[J].石油地球物理勘探,2005,8(4):483-489.
    [2]袁野,刘洋.地震属性优化与预测新进展[J].勘探地球物理进展,2010,(4):229-238.
    [3]白宝玲,赵洪洲.地震多属性综合分析技术在储层预测中的应用[J].石油天然气学报,2010,(1):246-248.
    [4]M Turhan Taner著.隗寿东摘译.地震属性[J].油气地球物理,2006,4(1):55-59.
    [5]赵加凡,陈小宏.基于灰关联分析与K-L变换的双重属性优化方法[J].石油地球物理勘探,2004,39(6):661-665.
    [6]何碧竹,周杰,汪功怀.利用多元地震属性预测储层信息[J].石油地球物理勘探,2003,38(3):258-262.
    [7]侯伯刚,杨池银,武站国,等.地震属性及其在储层预测中的影响因素[J].石油地球物理勘探,2004,39(5):553-558,574.
    [8]郎静,梁峰,候伯刚.油藏精细描述技术在歧南西斜坡隐蔽油气藏勘探中的应用[J].物探与化探,2006,30(2):123-128.
    [9]Dick D R,Olga K,Oleg O,et al.Supervised locally linearembedding[EB/OL].http://inpc55.et.tudelft.nl/research/papers/icann03.pdf,2003-08-15.
    [10]胡丹.基于改进的SLLE在地震属性优化中的研究与应用[D].成都:成都理工大学,2007.
    [11]Sam T R,Lawrence K S.Nonlinear dimensionalityanalysis by locally linear embedding.Science,2000,290(12):2 323-2 326.
    [12]Lawrence K S,Sam T R.An introduction to locallylinear embedding[EB/OL].http:www.cs.toron-to.edu/～roweislle,2001-06-10.
    [13]Olga Kouropteva,Oleg Okun,Matti Pietikinen.Selection of the optimal parameter value for the locallylinear embedding algorithm[A].Wang L,Halgamuge SK,Yao X.Proceedings of the 1st InternationalConference on Fuzzy Systems and Knowledge Discovery[C].Singapore:Computational Intelligence for the E-Age,2002.
    [14]邓星亮,吴清.LLE算法及其应用[J].测控技术,2005,24(3):65-66.
    [15]肖健.局部线性嵌入的流行学习算法研究与应用[D].北京:国防科技大学,2005.
    [16]谢季坚,刘承平.模糊数学方法及其应用[M].武汉:华中科技大学出版社,2000.