COMPARISON OF KRIGING TECHNIQUES IN A SPACE-TIME CONTEXT

Space-time processes constitute a particular class, requiring suitable tools in order to predict values in time and space, such as a space-t ime variogram or covariance function. The space-time covariance functi on is defined and linked to the Linear Model of Coregionalization unde r second-order space-time stationarity. Simple and ordinary space-time kriging systems are compared to simple and ordinary cokriging and the ir differences for unbiasedness conditions are underlined. The ordinar y space-time kriging estimation then is applied to simulated data. Pre diction variances and prediction errors are compared with those for or dinary kriging and cokriging under different unbiasedness conditions u sing a cross validation. The results show that space-time kriging tend to produce lower prediction variances and prediction errors that krig ing and cokriging.