多智能体与元胞自动机结合及城市用地扩张模拟

Integration of Multi-agent Systems with Cellular Automata for Simulating Urban Land Expansion

运用多智能体(Agent)和元胞自动机(CA)结合来模拟城市用地扩张的方法,将影响和决定用地类型转变的主体作为Agent引进元胞自动机模型中,Agent在CA确定的城市发展概率的基础上,通过自身及其周围环境的状况,综合各种因素的影响做出决策,决定元胞下一时刻的城市发展概率。运用Agent的决策结果,对CA模型中以随机变量体现的不确定性通过Agent决策行为给予地理意义的新解释。以城市郊区—樟木头镇为例,对1988～1993年城市用地扩张进行了模拟研究,取得了良好的模拟效果。

This paper demonstrates that urban land expansion can be well simulated by the integration of multi-agent systems with cellular automata （CA）. There are increasingly studies on using CA models to simulate urban development. Very plausible results can be generated, although there are still some limitations by using CA models alone. CA models have limitations by taking human and social factors into account in simulating complex urban systems. Agents can be used to simulate complex urban systems more effectively because human factors can be considered. An agent has the ability to make decisions by interacting itself with the environment and other agents. It could embody the uncertainties and complex behaviors in the simulation process. In this paper, agents are used to make decisions for determining land use changes by considering their economic factors, family conditions and the profit of land use conversion. These behaviors of these agents influence the probability of urban development in the model. Based on this Agent-CA model, urban development of Zhangmutou Town was simulated from 1988 to 1993. The result indicates that the simulation accuracy is much better than those of the traditional CA models. Moreover, the uncertainties of urban development can be well explained by using the agents.