Advanced spatial metrics analysis in cellular automata land use and cover change modeling

This paper proposes an approach for a more effective definition of cellular automata transition rules for landscape change modeling using an advanced spatial metrics analysis. This approach considers a four-stage methodology based on: (i) the search for the appropriate spatial metrics with minimal correlations; (ii) the selection of the appropriate neighborhood size; (iii) the selection of the appropriate technique for spatial metrics application; and (iv) the analysis of the contribution level of each spatial metric for joint use. The case study uses an initial set of 7 spatial metrics of which 4 are selected for modeling. Results show a better model performance when compared to modeling without any spatial metrics or with the initial set of 7 metrics.

• Autores: Zamyatin, Alexander; Cabral, Pedro
• Tipo de recurso: Article of journal
• Fecha de publicación: 2011
• Institución: Universidad Nacional de Colombia
• Repositorio: Universidad Nacional de Colombia
• Idioma: spa
• OAI Identifier: oai:repositorio.unal.edu.co:unal/40449
• Acceso en línea: https://repositorio.unal.edu.co/handle/unal/40449; http://bdigital.unal.edu.co/30546/
• Palabra clave: LUCC modeling; spatial metrics; geocomputation; spatial metrics contribution level
• Rights: openAccess
• License: Atribución-NoComercial 4.0 Internacional