半变异函数模型参数估计的综合定权法  

A synthetic weighting method for parameter estimating of semivariogram model

作　　者：倪福泽 NI Fuze(Aerial Photogrammetry and Remote Sensing Research Institute Company Limited,Xi’an Shaanxi 710100,China)

机构地区：[1]中煤(西安)航测遥感研究院有限公司,陕西西安710100

出　　处：《北京测绘》2023年第7期1022-1025,共4页Beijing Surveying and Mapping

摘　　要：针对半变异函数参数估计时点对数法定权未能顾及滞后距的影响,可能无法反应滞后距较小几个点重要性的问题,对多项式回归法的权重进行优化。通过平行四边形法则综合点对数和滞后距的影响,给出一种综合定权法。以球面模型为例,通过不同定权方法估计半变异函数模型参数,实验结果表明综合定权法各点权重更合理,克里金估值也更接近实测值。Estimating the parameter of semivariogram model is defective when calculate weight by the number of pairs of points because it's failure to take into account the lag distance.The importance of point with small lag distance was decrease.It‘s necessary to improve weighting method of polynomial regression.A synthetic weighting method was derived by using parallelogram law to connecting the number and lag distance.Taking the spherical model as an example,we calculated the parameter of semivariogram model by different weighting methods.The experimental results indicated that weight by synthetic weighting method was more reasonable than others,and interpolating prediction by Kriging was more accurate.

关 键 词：半变异函数 权重 加权总体最小二乘 平行四边形法则 球面模型 

分 类 号：P207[天文地球—测绘科学与技术]