基于网络K函数法的地理对象分布模式分析——以香港岛餐饮业空间格局为例  

Spatial Pattern Analysis of Geographic Features Using Network K-Function Methods with a Case Study of Restaurant Distribution in Hong Kong Island

作　　者：邬伦[1] 刘亮[1] 田原[1] 肖晨超[2] 刘磊[1] 

机构地区：[1]北京大学遥感与地理信息系统研究所,北京100871 [2]中国国土资源航空物探遥感中心,北京100083

出　　处：《地理与地理信息科学》2013年第5期7-11,共5页Geography and Geo-Information Science

基　　金：中国地质调查局地质调查工作项目"全球矿产资源遥感探测支撑系统关键技术研究(1212011120214)";国家863项目"地理数据转换与可视化并行技术和中间件"(2011AA120301)

摘　　要：很多地理对象的空间分布与空间上呈现网状结构的地理现象高度相关,分析这些地理对象的分布模式,在地理研究中有重要意义。该文采用由平面空间扩展到网状结构空间的网络K函数法,以香港岛餐饮业地理空间格局为例开展研究。应用单变量K函数法分析餐饮店在网状结构空间中的分布模式,应用双变量交叉K函数法分析餐饮店分布是否受交通站点及旅游景点影响,并对不同尺度下餐饮店地理选址和空间分布规律进行探索与分析。Spatial distributions of many geographic features are highly related to geographical phenomena with network struc- tures. In this paper, two network K-function methods, the univariate network K-function method and the bivariate network K- function method, are applied to analyze spatial patterns of these geographic features. In a case study of restaurants distribution in Hong Kong Island,the univariate network K-function method is adopted to analyze the spatial distribution pattern of restau- rants,while the bivariate network K-function method is applied to analyze whether the distribution of restaurants is related to other spatial features such as bus stops and scenic spots. The distribution patterns of restaurants under different spatial scales are also discussed. It can be clearly concluded that the spatial distribution of restaurants is highly related to transport network under all spatial scales and is apparently related to bus stops on the transport network under relatively smaller spatial scale. The spatial relationship between the spatial distribution of restaurants and scenic spots is dependent on spatial scale. The spatial dis- tribution of restaurants is mutually exclusive to scenic spots under small spatial scales and is highly related to them under large spatial scales. This paper may provide references for further studies of this kind.

关 键 词：K函数 网状结构空间 点模式 空间分布 

分 类 号：P208[天文地球—地图制图学与地理信息工程]