基于偏最小二乘地理元胞模型的城市生长模拟  

Modelling Urban Growth Based on Geographical Cellular Automata with Partial Least Squares Regression

作　　者：冯永玖[1,2] 童小华[1] 刘妙龙[1] 

机构地区：[1]同济大学测量与国土信息工程系,上海200092 [2]上海海洋大学海洋科学学院,上海201306

出　　处：《同济大学学报（自然科学版）》2010年第4期608-612,共5页Journal of Tongji University:Natural Science

基　　金：国家自然科学基金资助项目(40771174);教育部新世纪优秀人才计划资助项目(NCET-06-0381);教育部博士点基金资助项目(20070247046);上海高校选拔培养优秀青年教师科研专项基金资助项目(ssc09018)

摘　　要：提出了一种基于偏最小二乘回归(PLS)方法的地理元胞(cellular automata,CA)模型PLS-CA,并用来模拟城市生长和扩展.CA模型的定义涉及存在严重相关性的众多空间变量,而传统的多准则判别技术(MCE)和主成分分析(PCA)不能够彻底地解决变量相关性问题.利用偏最小二乘回归从空间变量中提取线性无关的主成分,从而获取地理元胞自动机(CA)的转换规则,在地理信息系统(GIS)环境下建立PLS-CA模型,可以优化城市生长和扩展的模拟.利用提出的PLS-CA模型,模拟了上海市嘉定区1989年与2006年城市生长和扩展情况.Based on partial least squares regression, a novel geographical cellular automata model （PLS- CA） is proposed for simulating urban growth and expansion. In definition of cellular automata （CA） transition rules, numerous highly correlated independent spatial variables are utilized for obtaining more actual simulation results. Conventional methods,such as multi-criteria evaluation（MCE） and principal component analysis （PCA）, have difficulties in removing the harmful effects of correlation. Using partial least squares regression （PLS） integrated with CA and geographical information system （GIS）, a new CA model is created foroptimizing the simulation of urban growth and expansion. The PLS-CA model has been successfully applied to simulating urban growth of Jiading district, Shanghai from 1989 to 2006. And the simulation results show that the accuracy of PLS-CA is higher than that of conventional CA models.

关 键 词：城市生长模拟 元胞自动机 偏最小二乘回归 地理信息系统 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]