Modeling the spatial correlation structure of coregionalized data is a frequent task in numerous fields of the natural sciences. Even in the isotropic case, experimental covariances may exhibit complex features, such ...
详细信息
Modeling the spatial correlation structure of coregionalized data is a frequent task in numerous fields of the natural sciences. Even in the isotropic case, experimental covariances may exhibit complex features, such as a maximum cross-correlation attained at non-collocated locations (dimple or hole effect). Current construction principles for multivariate covariance models on Euclidean spaces do not allow accounting for such a property. We propose a spectral approach to modify cross-covariancefunctions of the isotropic bivariate Matern model in order to obtain a cross-dimple. Our model admits analytic expressions in terms of special functions. Our findings are illustrated through applications to data sets from the fields of mining and geochemistry. (C) 2021 Elsevier B.V. All rights reserved.
We propose new covariancefunctions for bivariate Gaussian random fields that are very general and include as special cases other popular models proposed in earlier literature, namely, the bivariate Matern and bivaria...
详细信息
We propose new covariancefunctions for bivariate Gaussian random fields that are very general and include as special cases other popular models proposed in earlier literature, namely, the bivariate Matern and bivariate Cauchy models. The proposed model allows the covariance margins to belong to different parametric families with. To our knowledge, this is the first model of this type to be proposed in the literature. For instance, one of the margins can be of the Matern type, whereas the latter can index long-range dependence. Estimation of the model is illustrated through simulation.
暂无评论