Spatial-temporal Statistics and Analysis of Rainfall in Jilin Province

Rainfall is one of important environmental phenomena with both spatial and temporal characteristics. It can be regarded as a realization of spatial-temporal random function. In order to analyze the rainfall in Jilin Province, a spatial-temporal covariance model is applied to describe the space-time correlation and the kriging is extended to 3-D for estimation and prediction. The monthly rainfall data used in this paper are taken at 24 monitoring stations from January 2001 to December 2008. During the experiment, the seasonal component of rainfall measurements is removed firstly, and the residuals are generated to model the spatial-temporal covariance. The 3-D kriging is used to interpolate the rainfall value for all stations in March 2008. And the interpolation accuracy is computed. which shows the method in spatial-temporal analysis of the rainfall is practical.