考虑边界效应的运输联系网络建模及其复杂特性

Study on Modelling and Complex Characteristics of Transport Linkage Network Considering Boundary Effect

边界效应是城市化进程中运输交流动态演变的必然结果,考虑边界效应的运输联系网络结构特征研究是运输组织优化和基础设施空间布局的关键。聚焦于区域运输联系在拓扑空间下的动态演变,将网络空间尺度的确定流程引入到传统运输联系网络的构建方法体系中,建立了考虑边界效应的区域运输联系网络的建模流程及方法。在此基础上,利用复杂网络理论,从无标度特性和小世界特性两个角度,构建了区域运输联系网络复杂特性的分析方法。以云南省为案例地区进行了实证分析,并将获取的网络复杂特性与传统运输联系网络构建方法获取结果进行了对比分析。结果表明:(1)城市尺度网络介于随机网络和无标度网络之间,正处于简单随机结构向复杂有序结构的转化期,且县域尺度网络呈现显著的无标度特性。(2)城市尺度和县域尺度下的运输联系网络均表现出小世界特征,但城市尺度网络表现出更小的平均路径长度和更大的聚类系数,说明其货运交流的运行效率优于县域尺度网络。(3)若不考虑跨界运输联系,城市尺度和县域尺度下运输联系网络的平均路径长度将偏小,网络的运营效率将被高估,县域尺度网络的小世界特征判断也将被误判,一定程度上验证了边界效应在运输联系特征刻画中的不可忽视性。

Boundary effect is the inevitable result of dynamic evolution of transport communication in the process of urbanization. The study of the structural characteristics of transport linkage network considering boundary effect is the key to the optimization of transport organization and the spatial layout of infrastructure.Focusing on the dynamic evolution of regional transport linkages in the topological space,the determination process of network spatial scale is introduced into the construction method system based on traditional transport linkage network,and the modelling process and the method of regional transport linkage network considering boundary effect is established. On this basis,a method to analyse the complexity of transport linkage network is introduced from the aspects of scale-free property and small world characteristics,which relies mostly on the complex network theory. Taking Yunnan Province as the case area for empirical analysis,the result of network complexity property is compared with the result acquired by construction approach of traditional transport linkage network. The result shows that( 1) The city scale network is between random andscale-free networks,which is in a transition phase from simple random structure to complex ordered structure,and there is obvious scale-free property in county-scale network.( 2) The networks at county scale and city scale both have small world characteristics. However,the network at city scale has a shorter average path length but a larger clustering coefficient,indicating higher operating efficiency for goods exchange than the network at county scale.( 3) If the cross-border transport linkages are not considered,the average path length for networks both at county and city scales will be shorter,and their operating efficiency will be overrated. Meanwhile,the small world characteristics for network at county scale also will be bad estimated.It demonstrates that the boundary effect in describing the features of the transport linkages cannot be ignored.