Spatiotemporal models in the estimation of area precipitation

Since area precipitation measurements are difficult to obtain because of the large spatial and time variability of the precipitation field, the development of statistical methods for the optimal combination of weather radar and rain gauge measurements is a matter of great importance. This work presents area rainfall prediction methods based on kriging and cokriging techniques modified to account for the autoregressive temporal structure of the gauge measurement process. Hence, the suggested kriging-type predictor includes spatial observations both at the present time and at k lagged time instants. Such predictors are called of kth-order. Cokriging-type predictors developed in this article include the mixed cokriging and linkage cokriging predictors. Mixed cokriging combines 1st-order prediction and observations of a co-process. The linkage cokriging predictor is appropriate to deal with observations from any two different processes with proportional, yet unknown, expected values. This will be the case for the spatiotemporal models adopted in this work to describe rain gauges and radar measurements. Its expression is the same as the simple cokriging, but the usual conditions are replaced by a single linkage condition. Finally, we apply these methods to a storm of mixed type that occurred in 1992, for 99 h, over the Alenquer River basin region located north of Lisbon. Copyright (c) 2005 John Wiley & Sons, Ltd.