Prediction of spatio-temporal data on meshed surfaces using advection-diffusion SPDEs

This page contains supplementary materials to the preprint entitled “Prediction of spatio-temporal data on meshed surfaces using advection-diffusion SPDEs”, by M. PEREIRA, L. CLAROTTO and N. DESASSIS.

• Fig 1.1(B):Simulation of the presence of sulfate in the Earth atmosphere.

• Fig 2.1: Simulation of a solution to the advection-diffusion SPDE on a meshed sphere, represented from three different viewpoints on the surface.

• Fig 4.1: Simulation of a solution to the advection-diffusion SPDE on a meshed sphere, represented from three different viewpoints on the surface.

• Fig. 4.2: Spatio-temporal evolution of the covariance between a reference point (in blue) and the rest of the points in the domain, for the spatio-temporal model simulated in Fig 4.1. The color (red to blue) represent the value of the covariance.

• Fig. 5.1: Spatio-temporal kriging predictor from data sampled from a simulation of the SPDE model and with a measurement noise of standard-deviation $\sigma=0.1$. The blue points locate the places where the observations are taken.

• Fig. 6.1: AOD data (after preprocessing) on the globe represented from three different viewpoints on the surface.

• Fig. 6.2: Spatio-temporal kriging of AOD on the globe represented from three different viewpoints on the surface.