The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

The SPDE model with transparent barriers

Elias T Krainski

October-2024

The transparent barrier model

This model considers an SPDE over a domain \(\Omega\) which is partitioned into \(k\) subdomains \(\Omega_d\), \(d\in\{1,\ldots,k\}\), where \(\cup_{d=1}^k\Omega_d=\Omega\). A common marginal variance is assumed but the range can be particular to each \(\Omega_d\), \(r_d\).

From Bakka et al. (2019), the precision matrix is \[ \mathbf{Q} = \frac{1}{\sigma^2}\mathbf{R}\mathbf{\tilde{C}}^{-1}\mathbf{R} \textrm{ for } \mathbf{R}_r = \mathbf{C} + \frac{1}{8}\sum_{d=1}^kr_d^2\mathbf{G}_d , \;\;\; \mathbf{\tilde{C}}_r = \frac{\pi}{2}\sum_{d=1}^kr_d^2\mathbf{\tilde{C}}_d \] where \(\sigma^2\) is the marginal variance. The Finite Element Method - FEM matrices: \(\mathbf{C}\), defined as \[ \mathbf{C}_{i,j} = \langle \psi_i, \psi_j \rangle = \int_\Omega \psi_i(\mathbf{s}) \psi_j(\mathbf{s}) \partial \mathbf{s},\] computed over the whole domain, while \(\mathbf{G}_d\) and \(\mathbf{\tilde{C}}_d\) are defined as a pair of matrices for each subdomain \[ (\mathbf{G}_d)_{i,j} = \langle 1_{\Omega_d} \nabla \psi_i, \nabla \psi_j \rangle = \int_{\Omega_d} \nabla \psi_i(\mathbf{s}) \nabla \psi_j(\mathbf{s}) \partial \mathbf{s}\; \textrm{ and }\; (\mathbf{\tilde{C}}_d)_{i,i} = \langle 1_{\Omega_d} \psi_i, 1 \rangle = \int_{\Omega_d} \psi_i(\mathbf{s}) \partial \mathbf{s} . \]

In the case when \(r = r_1 = r_2 = \ldots = r_k\) we have \(\mathbf{R}_r = \mathbf{C}+\frac{r^2}{8}\mathbf{G}\) and \(\mathbf{\tilde{C}}_r = \frac{\pi r^2}{2}\mathbf{\tilde{C}}\) giving \[ \mathbf{Q} = \frac{2}{\pi\sigma^2}( \frac{1}{r^2}\mathbf{C}\mathbf{\tilde{C}}^{-1}\mathbf{C} + \frac{1}{8}\mathbf{C}\mathbf{\tilde{C}}^{-1}\mathbf{G} + \frac{1}{8}\mathbf{G}\mathbf{\tilde{C}}^{-1}\mathbf{C} + \frac{r^2}{64}\mathbf{G}\mathbf{\tilde{C}}^{-1}\mathbf{G} ) \] which coincides with the stationary case in Lindgren and Rue (2015), when using \(\tilde{\mathbf{C}}\) in place of \(\mathbf{C}\).

Implementation

In practice we define \(r_d\) as \(r_d = p_d r\), for known \(p_1,\ldots,p_k\) constants. This gives \[ \mathbf{\tilde{C}}_r = \frac{\pi r^2}{2}\sum_{d=1}^kp_d^2\mathbf{\tilde{C}}_d = \frac{\pi r^2}{2} \mathbf{\tilde{C}}_{p_1,\ldots,p_k} \textrm{ and } \frac{1}{8}\sum_{d=1}^kr_d^2\mathbf{G}_d = \frac{r^2}{8}\sum_{d=1}^kp_d^2\mathbf{\tilde{G}}_d = \frac{r^2}{8}\mathbf{\tilde{G}}_{p_1,\ldots,p_k} \] where \(\mathbf{\tilde{C}}_{p_1,\ldots,p_k}\) and \(\mathbf{\tilde{G}}_{p_1,\ldots,p_k}\) are pre-computed.

References

Bakka, H., J. Vanhatalo, J. Illian, D. Simpson, and H. Rue. 2019. “Non-Stationary Gaussian Models with Physical Barriers.” Spatial Statistics 29 (March): 268–88. https://doi.org/https://doi.org/10.1016/j.spasta.2019.01.002.
Lindgren, Finn, and Havard Rue. 2015. Bayesian Spatial Modelling with R-INLA.” Journal of Statistical Software 63 (19): 1–25.

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.