摘要
数据内插被广泛应用于地统计分析领域,克里金插值作为其中最为有效的方法之一,其原理是通过建立变异函数理论模型,得到可靠的权重值和拉格朗日系数,构成求解待测点的线性组合。为了有效地提高插值精度,文中利用加权最小二乘法优化遗传算法中的适应度函数,进而改进普通基于遗传算法优化的克里金插值方法。并且在MATLAB中利用外部工具箱确定模型参数,最后通过实例验证,将该方法与普通克里金插值以及遗传克里金插值结果进行对比,发现采用该方法,插值效果较好且误差也较小,证明了通过加权最小二乘法可以有效改进普通遗传克里金插值方法。
Data interpolation is widely used in the field of geostatistical analysis.As one of the most effective methods of data interpolation,using Kriging could obtain reliable weight values to build up the linear combination by means of the establishment of semi-variogram model.In order to improve the accuracy of interpolation,weight least square is used in this paper to optimize the fitness function in genetic algorithm,then improve Kriging optimized by genetic algorithm only.Model parameters can be calculated by toolbox in MATLAB.Finally,verified by example data and compared with ordinary Kriging and genetic algorithm Kriging,this method is found to achieve a more interpolation result and get less error.Weight least square is proved to be an effective method to improve ordinary genetic algorithm Kriging.
出处
《计算机技术与发展》
2012年第3期92-95,共4页
Computer Technology and Development
基金
国家重点基础研究发展计划(973计划)项目(2010CB951603)
