Fast kriging of large data sets with Gaussian!Markov random fields
Fast kriging of large data sets with Gaussian!Markov random fields
复制标题
DOI：
10.1016/j.csda.2007.09.018
复制
发表时间：
2008-01-20
影响因子：
1.8
通讯作者：
Hossjer, Ola
中科院分区：
文献类型：
--
作者：
Hartman, Linda;Hossjer, Ola
空间数据集在许多科学学科中得到分析。克里格法，即最小均方误差线性预测，可能是最广泛使用的空间预测方法。计算时间和内存需求可能是一个障碍，克里金法的数据集与许多观察。通过使用格点上的高斯马尔可夫随机场作为高斯场的近似，加速了计算并降低了存储器需求。该算法也非常适合非晶格数据时，利用双线性插值在非晶格位置。(c)2007 Elsevier B.V.保留所有权利。
Spatial data sets are analysed in many scientific disciplines. Kriging, i.e. minimum mean squared error linear prediction, is probably the most widely used method of spatial prediction. Computation time and memory requirement can be an obstacle for kriging for data sets with many observations. Calculations are accelerated and memory requirements decreased by using a Gaussian Markov random field on a lattice as an approximation of a Gaussian field. The algorithms are well suited also for nonlattice data when exploiting a bilinear interpolation at nonlattice locations. (c) 2007 Elsevier B.V. All rights reserved.