Title

Spectral-spatial clustering of regionalized mixed data

Document Type

Conference Proceeding

Publication Title

Proceedings of IAMG 2019 - 20th Annual Conference of the International Association for Mathematical Geosciences

Publisher

International Association for Mathematical Geosciences (IAMG)

School

School of Science

Comments

Originally published as: Talebi, H., Peeters, L.J.M., Mueller, U., Tolosana-Delgado, R., & van den Boogaart, K.G. (2019). Spectral-spatial clustering of regionalized mixed data. Paper presented at the 20th Annual Conference of the International Association for Mathematical Geosciences, IAMG 2019. State College: United States.

Abstract

Spatial clustering groups similar spatial objects and/or patterns into distinct, spatially coherent clusters and is an important component of spatial data analysis in the earth sciences. Spectral clustering is a popular modern clustering algorithm, which relies on graph-theoretical concepts. It outperforms traditional clustering algorithms, but generally does not account for spatial relationships. The aim of this study is to improve the spatial awareness of the spectral clustering by utilising a dissimilarity matrix based on nonparametric higher order spatial statistics. The proposed model-free technique can identify meaningful spatial clusters (i.e., meaningful geographical subregions) from multivariate spatial data of different scales without the need to define a model of co-dependence.

Share

 
COinS