Variance modeling for nonstationary spatial processes with temporal replications
Variance modeling for nonstationary spatial processes with temporal replications
复制标题
DOI：
10.1029/2002jd002864
复制
发表时间：
2003-10-24
影响因子：
4.4
通讯作者：
Guttorp, P
中科院分区：
文献类型：
--
作者：
Damian, D;Sampson, PD;Guttorp, P
[1]我们以前已经为高斯空间过程的非平稳相关函数r(x，x‘)的Sampson和Guttorp模型制定了贝叶斯方法[Damian et al.，2001]。该模型假设非平稳性可以通过双射空间变形f来编码，f定义了一个新的坐标系，在该坐标系中空间相关函数可以被认为是各向同性的，即r(x，x‘)=Rho(并行TOF(X)-f(x’)平行于)，其中r属于已知的参数族。我们对该模型进行了扩展，将空间异质性纳入到特定地点的时间差异中。在我们的贝叶斯框架中，方差被认为是另一个空间过程的(隐藏的)实现，我们将其建模为对数-高斯，相关结构以观察到的过程的相同空间变形函数来表示。我们在仿真和应用中对该方法进行了演示。
[1] We have previously formulated a Bayesian approach to the Sampson and Guttorp model for the nonstationary correlation function r(x, x') of a Gaussian spatial process [Damian et al., 2001]. This model assumes that the nonstationarity can be encoded through a bijective space deformation, f, that defines a new coordinate system in which the spatial correlation function can be considered isotropic, namely r(x, x') = rho(parallel tof (x) - f (x')parallel to), where r belongs to a known parametric family. We extend this model to incorporate spatial heterogeneity in site-specific temporal variances. In our Bayesian framework the variances are considered ( hidden) realizations of another spatial process, which we model as log-Gaussian, with correlation structure expressed in terms of the same spatial deformation function underlying that of the observed process. We demonstrate the method in simulations and in an application.