Urban Land Expansion Model Based on Multi- agent System and Application
多智能体城市土地扩张模型及其应用

The traditional urban land expansion model has paid much attention on a static state, and few scholars have focused research on land use change situations through time. Although the urban land expansion model based on cellular automata performs dynamic feature, the model fails to display the multivariate change results produced from different agents' behaviors. On account of the above reasons, this research has built up a set of spatial-temporal land resource allocation rule and developed a dynamic urban land expansion model based on multi-agent system, which can simulate the interactions among agents. What's more, this model is applied to analyze and simulate urban land expansion process taking downtown of Changsha city as a study area. The results show that this model can not only reflect basic characteristics of urban land expansion, but also help to explain the reasons for urban land expansion process and understand the effect of agents' behavior on urban land expansion, what's more, in contrast to simulation results with land use classification map from remote sensing images, the accuracies of the simulation reached over 68% according to the cell-by-cell comparison, which makes it possible to provide land use decision-make support to government and urban planners.