A novel algorithm for calculating transition potential in cellular automata models of land-use/cover change. (February 2019)

• Record Type: Journal Article
• Authors: Roodposhti, Majid Shadman; Aryal, Jagannath; Bryan, Brett A.
• Is Part Of: Environmental modelling & software. Volume 112(2019)
• Page Start: 70
• Page End: 81
• Publication Date: 2019-02
• Subjects: Entropy -- Land-use/cover change -- Uncertainty -- Urban planning -- Modelling -- Simulation; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2018.10.006
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: Despite recent advances in quantifying land-use/cover change (LUCC) transition potential, transition rules are often not transparent and uncertainty is rarely made explicit. Here, we introduce DoTRules—a dictionary of trusted rules—as a transparent alternative to calculate transition potential in cellular automata models. Rules relate LUCC variables to the observed historical changes. Shannon entropy is calculated to assess the uncertainty of each rule, and the most trusted rules are used to project future LUCC. DoTRules produces rule-level uncertainty estimates, which can be mapped. In a case study of the Ahvaz region of Iran, the overall accuracy of LUCC simulation calibrated using DoTRules was very similar to simulations calibrated with the state-of-the-art random forest, but DoTRules provides a more transparent approach where transition rule information and uncertainty can be readily accessed and interpreted. The results demonstrate that DoTRules has potential to derive new insights into LUCC processes. Highlights: DoTRules calculates transition potential in CA-based land-use models. DoTRules-based simulation performance was similar to random forest-based. DoTRules generates transparent transition rules and quantifies uncertainty. Uncertainty estimates were correlated with land-use simulation accuracy. Uncertainty estimates can reduce the need for ground-truthed validation.