Abstract
In this paper, an efficient and effective Gaussian Kriging metamodeling approach is proposed in the framework of Bayesian maximum a posterior. Different prior densities and particularly, a Jeffreys' noninformative density based hierarchical prior is imposed respectively on the regression coefficients in the mean model and the correlation parameters in the covariance matrix of Gaussian Kriging. And the involved parameters are estimated by the expectation maximization and Fisher's scoring algorithms. Compared against several benchmark and recent methods in literature, the proposed approach is shown capable of simultaneous high prediction accuracy and low computational cost.
