Desenvolvimento do padrão de crescimento urbano: modelação da dinâmica do solo urbano em Andaluzia

Dissertação apresentada como requisito parcial para obtenção do grau de Mestre em Ciência e Sistemas de Informação Geográfica

From the diverse range of approaches available to model land use changes models, in this study the objective is to highlight the potential of a specific toll to predict changes in land use, Artificial Neural Networks. The purpose of this study is to evaluate the effectiveness of Artificial Neural Networks to predict urban land changes at regional scale, using different calibrations of the Land Transformation Model. This model uses a learningmachine to quantify and model the behavior and the complex patterns of land use and the Geographic Information System to manage the database, develop predictive variables, spatial analysis and to evaluate the results. The LTM was parameterized to the Andalusia region, to explore how factors such as line of the coastline, watercourses, roads, highways, urban land, recreational areas, population density, the railroads, airports, forest soil, agricultural soil, big cities, can influence urbanization pattern, using two different periods, from 1987 to 2003 and 1995 to 2003. (...)