The assessment of changes in the landscape is the efficiency key in land management. The goal of this work is to parameterize and calibrate a model of land cover and land use change, and validate the predictive scenarios associated with sugarcane expansion in Arealva-SP, from 2005 to 2010. The initial and final maps were co-registered and, after rasterization, we conducted a cross-tabulation, generating a map of changes and the respective transition matrix. The model adopted was Dinamica EGO and its performance was evaluated by means of a method based on the concept of fuzziness of location, in which the representation of a cell is influenced by itself, and to a lesser extent, by its neighborhood. There is a predominance of pastures and a reduced presence of native vegetation. The most relevant changes are related to sugarcane expansion and reduction of pastures. The value of the fuzzy similarity index extracted for the comparison between the simulated map and the reference-map for a window size of 11x11 pixels and using a constant decay function was 0.52. This simulation experiment enabled us to acquire a deeper knowledge on the drivers of land cover and land use change.