A methodological approach in order to define a geographical territorial structure classification through an application in the south of Brazil

Abstract

Traditionally, the territorial classification is achieved by analysing the land use and spatial statistical information according general classification principles. However, the use of miscellaneous territorial information can be problematic to achieve a good methodological approach. In that context, a methodological approach that makes use of an unsupervised classification of digital information is proposed. A type of classifier is used in order to uncover commonly occurring and distinctive territorial patterns on the assumption that these represent major territorial structures classes. The proposed approach is tested in a case study carried out in the South of Brazil. All the municipalities were classified and grouped within areas according to similar condition of urban preponderance and socioeconomic parameters. The identification of those areas, which constitutes an option to avoid the confrontations that may be derived from the essentially subjective political criteria, can be important to develop common sustainable strategies and advances in municipality partnerships.