文档介绍：两种空间插值方法的比较研究
魏继德
(福州大学福建省空间信息工程研究中心空间数据挖掘与信息共享教育部重点实验室,福州 35002)
摘要:距离倒数加权法算法简单,容易实现,适合分布较均匀的采样点集,但容易出现“牛眼”现象;克里金法是一种无偏最优估计法,精度较高,适合空间自相关程度高的数据,但其算法复杂,实现较难。这两种方法各有其适用情形,本文比较了这两种方法的优劣并提出算法优化的思路。
关键字:距离倒数加权,克里金,优化
The research parison of two spatial interpolation approaches
Wei Jide
(Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Spatial Information
Research Center of Fujian Province, Fuzhou 350002, China)
Abstract:As a simple and easily-implemented spatial interpolation algorithm, inverse-distance weighting fits for evenly-distributed sampling points, but it is prone to generate "bovine" phenomenon. Kriging is an unbiased optimal estimation method. It is accurate for data with a high degree spatial autocorrelation, but plicated and thus more difficult to implement. Either of them has its own applying circumstances. This pares the advantages and disadvantages between both of them, and presents the idea of optimizing the algorithms.
Keyword:Inverse-distance weighting,Kriging,Optimization
1引言网
比得anc=atial Interpor
空间插值是根据一组已知的离散数据或分区数据,按照某种假设推求出其他未知点或未知区域的数据的过程,简单的说就是由已知空间特性推求未知空间特性。它是地学研究中的基本问题,也是G