B0756
Title: Fully non-separable Gneiting covariance functions for multivariate space-time data
Authors: Denis Allard - INRAE (France) [presenting]
Lucia Clarotto - Mines Paris, PSL University (France)
Xavier Emery - Universidad de Chile (Chile)
Abstract: The well-known Gneiting class of space-time covariance functions is broadened by introducing a very general parametric class of fully nonseparable direct and cross-covariance functions for multivariate random fields, where each component has a spatial covariance function from the Matern family with its own smoothness and scale parameters and, unlike most currently available models, its own correlation function in time. It is shown that pseudo-variograms are involved in the temporal structure, and we discuss the estimation of the parameters. The application of the proposed model is illustrated on a weather trivariate dataset over France. The new model yields better fitting and better predictive scores compared to a more parsimonious model with a common temporal correlation function.
