地理学报 ›› 2008, Vol. 63 ›› Issue (8): 882-894.doi: 10.11821/xb200808009

• GIS应用 • 上一篇    

人工免疫系统与嵌入规划目标的城市模拟及应用

刘小平, 黎夏, 张啸虎, 陈刚强, 李少英, 陈逸敏   

  1. 中山大学地理科学与规划学院, 广州510275
  • 收稿日期:2007-10-27 修回日期:2008-05-23 出版日期:2008-08-25 发布日期:2008-08-25
  • 通讯作者: 黎夏, 男, 教授, 从事遥感和地理信息系统研究, 已发表GIS 和遥感论文170 多篇。 E-mail: lixia@mail.sysu.edu.cn
  • 作者简介:刘小平(1978-), 男, 湖南邵阳人, 副教授。研究方向为遥感和地理信息系统。E-mail: yiernanh@163.com
  • 基金资助:

    国家杰出青年基金项目(40525002); 国家自然科学基金项目(40471105); 国家高技术研究发展计划(863 计 划) (2006AA12Z206)

Embedding Urban Planning Objective by Integrated Artificial Immune System and Cellular Automata

LIU Xiaoping, LI Xia, ZHANG Xiaohu, CHEN Gangqiang, LI Shaoying, CHEN Yimin   

  1. School of Geography and Planning,Sun Yat-sen University,Guangzhou 510275,China
  • Received:2007-10-27 Revised:2008-05-23 Online:2008-08-25 Published:2008-08-25
  • Supported by:

    National Outstanding Youth Foundation of NSF of China, No.40525002; National Natural Science Foundation of China, No.40471105; Hi-Tech Research and Development Program of China, No.2006AA12Z206

摘要:

人工免疫系统(AIS) 具有强有力的计算能力, 可以通过免疫识别、克隆选择、免疫学 习、免疫记忆等功能来进行模式识别和自适应学习。AIS 所具有的自学习、自适应和记忆的能力非常适合于复杂地理过程的研究。而元胞自动机(CA) 是研究复杂系统非常方便和有效的工具。将人工免疫系统和元胞自动机相结合, 建立了城市演变的模拟和规划模型。该模型通过改变抗体的进化变异机制, 把规划目标嵌入到AIS 算法中, 抗体将会逐渐朝着规划目标“进化”, 从而模拟出基于不同规划情景的城市发展空间格局, 为城市和土地利用规划提供决 策支持。设计了6 种不同的城市发展方案, 利用该模型模拟了不同规划方案下珠江三角洲城市的发展情景(1988-2002 年)。并比较了不同模拟情景结果城市的紧凑性: “城市中心” 和 “城市中心—高速公路”发展模式的城市形态更为紧凑, 破碎度较低; 而“镇中心” 和“道路”发展模式形成的城市形态则比较凌乱和分散。模拟结果和分析表明: “城市中心—高速 公路”是珠江三角洲最适合的城市发展模式。

关键词: 人工免疫系统, 规划目标, 元胞自动机, 城市模拟, 珠江三角洲

Abstract:

A rtificial Im m une System can be used in pattern recognition and self-adaptive learning for its strong com puting pow er such as im m une recognition,clonal selection,im m une learning and im m une m em ory, w hich is quite suitable for studying the com plex geographical progress.A nd C A is proved to be convenient and effective for studying com plex system . A s a result, m odel based on integrating A IS w ith CA was built to sim ulate the urban evolution and planning in this paper.A s planning objective w as em bedded into A IS algorithm , antibody w ill gradually evolve tow ards w hich by changing the evolutionary variation m echanism . Then urban developing spatial pattern based on different planning scenarios can be sim ulated,w hich w ill supply decision support for urban and land use planning.This paper designed six different scenarios for city developm ent, and used A IS-based C A m odel to sim ulate the Pearl R iver D elta's urban developm ent (1988-2002) under different planning scenarios. It also com pared the urban com pactness under different sim ulation results: "C ity C enter" and "C ity C enter- Expressw ay" m odels incline to result in a m ore com pact form of urban; O n the other hand, "Tow n C enter" and "R oad" m odels com e into being a relatively scattered and decentralized form of urban areas. Sim ulated results indicate that "C ity C enter- Expressw ay" is the best developm ent m ode for the Pearl R iver D elta.

Key words: A rtificial Im m une System, urban planning objective, cellular autom ata, Pearl R iver D elta, urban sim ulation