SIMULATING URBAN LAND USE CHANGE THROUGH CA-BASED MODELING AND LOGISTIC REGRESSION

Simulating urban land use change through stochastic methods invariably demands the assessment of spatial land use transition probabilities. This has been accomplished to date mostly by empirical calculations and statistical linear methods. In the present work, we introduce a framework for simulating urban land use dynamics based on the estimation of land use transition probabilities through logistic regression. These probabilities drive a cellular automaton (CA) simulation model, based on eight cell Moore neighborhoods and stochastic transition algorithms. A medium -sized town in the west of Sao Paulo State, Bauru, was adopted as case study. Different simulation outputs for the case study town in the period 1979-1988 were generated, and statistical validation tests were then conducted for the best results, employing a multiple resolution fitting procedure.