1 “Understanding and Modelling Urban Land Use Dynamics to Achieve Sustainability” Cláudia Maria de Almeida 1 , Antonio Miguel Vieira Monteiro 2 , Gilberto Câmara 3 , Britaldo Silveira Soares-Filho 4 , Gustavo Coutinho Cerqueira 5 , Cássio Lopes Pennachin 6 1 PhD Student in Remote Sensing and GIS – National Institute for Space Research (INPE) – almeida@ltid.inpe.br, phone: + 55-12- 3906-5725, fax: +55-12-3906-5725; 2 Division for Image Processing – National Institute for Space Research (DPI-INPE) – miguel@dpi.inpe.br, phone: +55-12-3945-6444, fax: +55-12-3945-6468; 3 gilberto@dpi.inpe.br, phone: +55-12-3945-6499, fax: +55-12-3945-6468, Av. dos Astronautas, 1758 – 12227-010, São José dos Campos, SP - Brazil 4 Department of Cartography – Federal University of Minas Gerais (UFMG) – britaldo@csr.ufmg.br, phone: +55-31-3499-5417, fax: +55-31-3499-5415; 5 Centre for Remote Sensing – Federal University of Minas Gerais (CSR-UFMG) – cerca@csr.ufmg.br, Av. Antônio Carlos, 6627 – 31270-900, Belo Horizonte, MG – Brazil 6 Intelligenesis do Brasil Ltda. – cassio@intelligenesis.net, Av. Brasil, 1438-1505, 30140-003, Belo Horizonte, MG – Brazil Abstract. This scientific paper, part of a PhD Thesis currently under execution at the Division for Image Processing of the Brazilian National Institute for Space Research (DPI – INPE), is committed with building up a methodological guideline for modelling urban land use dynamics. A medium-size town in the west of São Paulo State, Bauru, was adopted as case study. Its urban structure was converted into a 100 x 100 (m) resolution grid, and transition probabilities were calculated for each grid cell by means of the “weights of evidence” statistical method and upon basis mainly of the information related to the technical and social infrastructure of the town. The probabilities therefrom obtained fed a cellular automaton (CA) simulation model – DINAMICA- conceived by the Centre for Remote Sensing of the Federal University of Minas Gerais (CSR-UFMG), based on a multiscale vicinity approach and stochastic transition algorithms. 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. This modelling experiment revealed the plausibility of adopting Bayesian empirical methods based on the available infrastructure knowledge to simulate urban land use change, what implies their further applicability for generating forecasts of growth trends either for Brazilian towns or cities worldwide, so as to help planners and local authorities in achieving sustainability. Keywords: Urban Modelling,Urban Sustainability, Town Planning, Cellular Automata