摘要
针对原同位置协同克里金 (CollocatedCoKriging)法在研究区域大、硬数据少、择优采样严重的情况下 ,外推不可靠和贝叶斯克里金 (BayesianKriging)法在估计先验数据期望值时对尺度敏感的问题 ,根据这两种方法的原理提出并推导一种新的贝叶斯同位置协同克里金估值方法 .论述了该方法不但具有一般克里金法的性质 ,而且综合了前两种方法的优点 .通过实例验证 ,其估值效果良好 .
To deal with the problem of extrapolation of Collocated CoKriging in big area where there are a few hard data and optimal sampling is serious, and the expectation of soft data is sensitive to scales in Bayesian Kriging approach, this paper deduces Bayesian Collocated CoKriging on the basis of Collocated CoKriging and Bayesian Kriging, and argues that Bayesian Collocated CoKriging not only has the properties of Linear Kriging, but also combines the merits of Collocated CoKriging and Bayesian Kriging. An example is given, showing the effect is fine.
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2002年第4期343-347,共5页
Journal of Computer-Aided Design & Computer Graphics