Embedding urban planning objective by integrated artificial immune system and cellular automata

Artificial Immune System can be used in pattern recognition and self-adaptive learning for its strong computing power such as immune recognition, clonal selection, immune learning and immune memory, which is quite suitable for studying the complex geographical progress. And CA is proved to be convenient and effective for studying complex system. As a result, model based on integrating AIS with CA was built to simulate the urban evolution and planning in this paper. As planning objective was embedded into AIS algorithm, antibody will gradually evolve towards which by changing the evolutionary variation mechanism. Then urban developing spatial pattern based on different planning scenarios can be simulated, which will supply decision support for urban and land use planning. This paper designed six different scenarios for city development, and used AIS-based CA model to simulate the Pearl River Delta's urban development (1988-2002) under different planning scenarios. It also compared the urban compactness under different simulation results: "City Center" and "City Center-Expressway" models incline to result in a more compact form of urban; On the other hand, "Town Center" and "Road" models come into being a relatively scattered and decentralized form of urban areas. Simulated results indicate that "City Center-Expressway" is the best development mode for the Pearl River Delta.