Cellular Automata in Modeling and Predicting Urban Densification: Revisiting the Literature since 1971

The creation of an accurate simulation future urban growth is considered to be one the most important challenges last five decades that involves spatial modeling within a GIS environment. Even though built-up densification processes, or transitions from low high density, are critical for policymakers concerned with limiting sprawl, literature on models study reveals them focus solely expansion process. Although majority these have similar goals, they differ in terms implementation and theoretical assumptions. Cellular automata (CA) been proven successful at simulating dynamics projecting scenarios multiple scales. This paper aims revisit CA determine various approaches realistic prediction densification. general characteristics described respect analysis driving factors influence scenarios. also critically analyzes hybrid based such as Markov chain, artificial neural network (ANN), logistic regression (LR). Limitation uncertainties models, namely, neighborhood cell size, may minimized when integrated empirical statistical models. result this review suggests it useful use multinomial (MLR) order analyze model effects related Realistic simulations can achieved multidensity class labels