An Integrated Approach based on Markov Chain and Cellular Automata to Simulation of Urban Land Use Changes

Land use change is one of the most important scientific research themes in the field of global environmental change. Due to the presence of uncertainty and randomness in the real world, it is difficult to simulate land use change exactly. To address the spatial uncertainty and temporal randomness in land use change, we propose a model for simulating land use change based on Markov chain and cellular automata (CA), and describes its application to the simulation of land use changes in the city of Wuhan, China. To simulate the urban land use change, the transition rules of the model were first set by globally restrained conditions, locally restrained conditions and a random variable. And then land use patterns and changes were obtained from classified Landsat TM images. A spatial-temporal transition matrix was constructed from the classified images and was applied to the proposed model for simulating land use changes in the city of Wuhan. The experiment results show the validity and feasibility of the Markov-CA-based model for simulating urban land use change.