Abstract
The aim of this study was to model the urban sprawl patterns of the Metropolitan Region of São Paulo (MRSP) using a spatial modeling technique based on cellular automata (CA). Therefore, we used urban perimeter data related to the periods of 1881, 1905, 1929, 1949, 1974 and 2005 for the construction of four models. These models consider the combination of variables representing the initial state of the cell (urban or non-urban), the number of neighboring cells classified as urban and the number of neighboring cells classified as non-urban. A particular model, whose configuration considers the combination of the initial state of the cell with the number of neighboring cells classified as urban, had the best performance (i.e., 94% of correct predictions). Next, a land use forecast for 2030 was evaluated by this model, highlighting both infrastructure-oriented patterns of urban expansion and urban occupation processes in inappropriate areas. In summary, this study demonstrated that the method can serve as a tool in urban planning processes.
Keywords:
Urban sprawl; Spatial modeling; Cellular automata