普通Kriging法在空间插值中的运用  

Ordinary Kriging algorithm applied for interpolation

作　　者：弓小平[1] 杨毅恒[2] 

机构地区：[1]新疆大学地理学科博士后科研流动站,新疆乌鲁木齐830046 [2]北京信息科技大学理学院,北京100085

出　　处：《西北大学学报（自然科学版）》2008年第6期878-882,共5页Journal of Northwest University（Natural Science Edition）

基　　金：国家"863"基金资助项目(2002AA135160)

摘　　要：目的为提高矿产出储量计算的精确性。方法运用普通克里格法解决空间插值问题。针对地质人员采集数据信息的局限性,采用普通克里格插值方法弥补数据量的缺乏。对新疆贝克滩水系沉积物化探数据进行空间分析。结果预测值参数——均值为106.39,峰度为-0.30,最大值为148.76,标准差为27.57,偏度为-1.12,最小值为53.91;交叉验证法参数:指标值为10.86。结论通过交叉检验、QQ检验、预测直方图方法验证表明,采用普通克里格法得到的预测值效果较好。Aim To improve the accuracy of calculation of reserves. Methods Appling ordinary Kriging interpolation compensate for the lack of data. Ordinary Kriging is an exact interpolator; that is, Kriging estimates are unbiased, so the expected value of the estimates is the same as the expected value of the observations. Results Forecast parameters average is 106. 39, kurtosis is - 0. 30, Maximum is 148.76, standard deviation is 27.57, Skewness is - 1.12, minimum is 53.91 ; cross validation parameters：desired value is 10. 86. Conclusion By using of crossexamination, QQ-plot, forecast histogram, and the result show that Ordinary Kriging predicted to be better.

关 键 词：普通克里格法 插值 变异函数 球状模型 

分 类 号：P628.2[天文地球—地质矿产勘探]