%0 Journal Article
%4 sid.inpe.br/marciana/2004/01.12.15.36
%2 sid.inpe.br/marciana/2004/01.12.15.36.25
%@issn 1467-1298
%T Empiricism and Stochastics in Cellular Automaton Modeling of Urban Land Use Dynamics
%D 2002
%8 2002-02
%A Almeida, Maria Cláudia de,
%A Batty, Michael,
%A Câmara, Gilberto,
%A Monteiro, Antônio Miguel Vieira,
%A Soares Filho, Britaldo Silveira,
%A Pennachin, Cássio Lope,
%A Cerqueira, Gustavo Coutinho,
%@affiliation Instituto Nacional de Pesquisas Espaciais. Devisão de Sensoriamento remoto (INPE, DSR)
%@affiliation Instituto Nacional de Pesquisas Espaciais. Devisão de Processamento de Imagens (INPE, DPI)
%@affiliation Department of Cartography, Federal University of Minas Gerais (UFMG), Belo Horizonte, Minas Gerais
%@affiliation Intelligenesis do Brasil Ltda, Belo Horizonte, Minas Gerais
%@affiliation Centre for Advanced Spatial Analysis, University College London, UK
%B CASA Working Paper Series
%V 42
%P 42
%K land use change, transition probabilities, Bayes theorem, weights of evidence, cellular automata, urban growth, urban planning.
%X An increasing number of models for predicting land use change in regions of rapid urbanization are being proposed and built using ideas from cellular automata (CA) theory. Calibrating such models to real situations is highly problematic and to date, serious attention has not been focused on the estimation problem. In this paper, we propose a structure for simulating urban change based on estimating land use transitions using elementary probabilistic methods which draw their inspiration from Bayes' theory and the related weights of evidence approach. These land use change probabilities drive a CA model DINAMICA conceived at the Center for Remote Sensing of the Federal University of Minas Gerais (CSR-UFMG). This is based on a eight cell Moore neighborhood approach implemented through empirical land use allocation algorithms. The model framework has been applied to a medium-size town in the west of São Paulo State, Bauru. We show how various socio-economic and infrastructural factors can be combined using the weights of evidence approach which enables us to predict the probability of changes between land use types in different cells of the system. Different predictions for the town during the period 1979-1988 were generated, and statistical validation was then conducted using a multiple resolution fitting procedure. These modeling experiments support the essential logic of adopting Bayesian empirical methods which synthesize various information about spatial infrastructure as the driver of urban land use change. This indicates the relevance of the approach for generating forecasts of growth for Brazilian cities particularly and for world-wide cities in general.
%@language en
%3 CASA_Online.pdf
%O Online: http://www.casa.ucl.ac.uk/working_papers/Paper42.pdf