Geostatistics provides a coherent framework for spatial prediction and uncertainty assessment, whereby spatial dependence, as quantified by variograms, is utilized for best linear unbiased estimation of a regionalized...Geostatistics provides a coherent framework for spatial prediction and uncertainty assessment, whereby spatial dependence, as quantified by variograms, is utilized for best linear unbiased estimation of a regionalized variable at unsampled locations. Geostatistics for prediction of continuous regionalized variables is reviewed, with key methods underlying the derivation of major variants of uni-variate Kriging described in an easy-to-follow manner. This paper will contribute to demystification and, hence, popularization of geostatistics in geoinformatics communities.展开更多
There are various occasions where simple, ordinary, and universal kriging techniques may find themselves incapable of performing spatial prediction directly or efficiently. One type of application concerns quantificat...There are various occasions where simple, ordinary, and universal kriging techniques may find themselves incapable of performing spatial prediction directly or efficiently. One type of application concerns quantification of cumulative distribution function (CDF) or probability of occurrences of categorical variables over space. The other is related to optimal use of co-variation inherent to multiple regionalized variables as well as spatial correlation in spatial prediction. This paper extends geostatistics from the realm of kriging with uni-variate and continuous regionalized variables to the territory of indicator and multivariate kriging, where it is of ultimate importance to perform non-parametric estimation of probability distributions and spatial prediction based on co-regionalization and multiple data sources, respectively.展开更多
基金the National 973 Program of China (No. 2007CB714402-5).
文摘Geostatistics provides a coherent framework for spatial prediction and uncertainty assessment, whereby spatial dependence, as quantified by variograms, is utilized for best linear unbiased estimation of a regionalized variable at unsampled locations. Geostatistics for prediction of continuous regionalized variables is reviewed, with key methods underlying the derivation of major variants of uni-variate Kriging described in an easy-to-follow manner. This paper will contribute to demystification and, hence, popularization of geostatistics in geoinformatics communities.
基金Supported by the National 973 Program of China (No. 2007CB714402-5)
文摘There are various occasions where simple, ordinary, and universal kriging techniques may find themselves incapable of performing spatial prediction directly or efficiently. One type of application concerns quantification of cumulative distribution function (CDF) or probability of occurrences of categorical variables over space. The other is related to optimal use of co-variation inherent to multiple regionalized variables as well as spatial correlation in spatial prediction. This paper extends geostatistics from the realm of kriging with uni-variate and continuous regionalized variables to the territory of indicator and multivariate kriging, where it is of ultimate importance to perform non-parametric estimation of probability distributions and spatial prediction based on co-regionalization and multiple data sources, respectively.