Optimal designs for some bivariate cokriging models

This article focuses on the estimation and design aspects of a bivariate collocated cokriging experiment. For large class covariance matrices, linear dependency criterion is identified, which allows best unbiased estimator primary variable in setup to reduce univariate kriging estimator. Exact optimal designs for efficient prediction such simple ordinary reduced models with one-dimensional inputs are determined. Designs found by minimizing maximum integrated variance, where an Ornstein-Uhlenbeck process. known parameters, equispaced shown be both functions. The more realistic scenario unknown parameters addressed assuming prior distributions parameter vector, thus adopting Bayesian approach problem. proved criteria. work motivated designing water monitoring system Indian river.