利用von Karman模型的Kriging插值用于GPS高程拟合  

GPS elevation fitting model based on von Karman Kriging method

作　　者：张书毕[1,2] 张秋昭[2] 杨化超[1,2] 

机构地区：[1]江苏省资源环境信息工程重点实验室,江苏徐州221008 [2]中国矿业大学环境与测绘学院,江苏徐州221008

出　　处：《测绘科学》2010年第5期167-168,172,共3页Science of Surveying and Mapping

基　　金：地理信息工程国家测绘局重点实验室开放基金项目资助(200818)

摘　　要：针对传统的GPS高程拟合方法要求学习样本分布要均匀的缺点,以平滑自协方差函数为基础,应用基于von Karman模型的Kriging方法用于GPS高程拟合,提出"曲线法"来计算von Karman模型中的v值。通过某测区GPS联测水准数据的计算,与多项式曲面拟合法及传统半变异函数Kriging插值等方法比较,表明:基于vonKarman模型的Kriging方法,对于学习样本数据分布不均的地区拟合精度更高,更适合地形条件恶劣地区GPS高程拟合。Viewing from the defects of traditional GPS elevation fitting,based on smoother auto-covariance model,von Karman model was used in GPS elevation fitting by the Curve method to calculate parameter＂v＂of this model in the paper.Then taking an engineering example,methods of traditional polynominal curve fitting、Kriging method based on spherical model and power function model were compared in the paper respectively.Finally it was found out that Kriging method based on von Karman model has more sensitive reaction and better fitting precision especially in the regions with uneven distribution of sample data.

关 键 词：vonKarman模型 KRIGING方法 半变异函数 GPS高程 多项式曲面拟合 

分 类 号：P228.4[天文地球—大地测量学与测量工程]