半变异函数.doc

ADDIN CNKISM.UserStyle基于GIS的深圳企业空间分布格局研究 章 文1,2，王佳璆3 (1.中山大学地理科学与规划学院，广州510275；2.广东省城市化与地理环境空间模拟重点实验室，广州510275；3. 伦敦大学学院高级空间分析中心，伦敦 W1T 4TJ) 摘 要：区域经济逐步借助于地理信息系统（GIS）的空间统计分析方法，来研究经济现象的空间模式和非常态分布，基于2012年数字城市数据，采用区域密度模型、地统计学方法和空间聚类分析方法，从整体模型、方向变异性以及局域聚类类型三个方面展开对深圳企业空间分布格局的研究。结果表明：在同一数据来源下运用圈层距离采样法能提高区域密度模型拟合精度，同时计算结果显示相比人口密度深圳企业空间分布更符合克拉卡模型；通过半异函数揭示出深圳企业对周边地区亦产生影响力；聚类分析显示深圳偏离空间质心靠近香港的城区属于企业高-高值聚类和热点区域，这种空间格局与其他传统城市有所不同。 关键词：企业空间格局；区域密度模型；半变异函数；空间聚类分析；深圳 GIS Based Study on the Spatial Pattern of Shenzhen Enterprises ZHANG Wen1,2 ,WANG Jiaqiu3 (1. Geography and Planning School of Sun Yat-sen University, Guangzhou 510275, China; 2. Key Laboratory of Urbanization and Geographical Environment Simulation of Guangdong Province, Guangzhou 510275, China; 3. Centre for Advanced Spatial Analysis of University College London , London W1T 4TJ, Britain) Abstract: Regional economy uses gradually Geography Information System (GIS) spatial statistical methods to study the spatial pattern of economic phenomena and an unnormal distribution. Based on digital city data in 2012, the traditional regional density model, geostatistics and spatial cluster analysis are utilized to research spatial pattern of enterprises in Shenzhen from three aspects of spatial pattern, such as the overall model, orientational variability and local clustering type. The result shows that: using the circle distance sampling method under the same sources of data can improve the fitting precision of regional density model. Simultaneously the calculation result shows that Clark model fits Shenzhen enterprises spatial distribution more actually than population density. The range of Shenzhen enterprises semivariance is long which influences the surrounding area. Cluster analysis reveals that the Shenzhen center zone which is close to Hong Kong but deviates from space centroid belongs to high - high value of clustering and hot spots. This kind of Spatial Pattern is different from other traditional cities. 企业作为城市经济的基础细