Bagging Voronoi-classifiers for clustering spatial functional data

We consider the problem of clustering functional data indexed by the sites of a spatial finite lattice, motivated by the analysis of the environmental data contained in the Surface Solar Energy database (NASA 2010). To this purpose, we exploit the bagging Voronoi-classifiers algorithm introduced in Secchi et al. (2012), based on repeatedly partitioning the investigated area in random neighborhoods, and on replacing the original data set with a reduced one, composed by local representatives of neighboring data. In this way we obtain many different weak formulations of the analysis, whose results are then bagged together to give a conclusive strong analysis.