文章编号： 1672-5328（2020）05-0068-08

任智1, 2，钟鸣1, 2，李大顺1, 2，刘少博1, 2，郑猛3，马晓凤1, 2
(1. 武汉理工大学智能交通系统研究中心，湖北武汉430063；2. 武汉理工大学国家水运安全工程技术研究中心， 湖北武汉430063；3.武汉市交通发展战略研究院，湖北武汉430017)

摘要： 如何获取并更新城市交通小区人口与就业岗位分布数据是当前交通规划工作面临的难题。首 先分析土地利用、可达性、建筑面积与城市人口和就业岗位分布的关系。在空间消费系数的基础 上，考虑可达性对人口和就业岗位分布的影响，提出人口、就业岗位增量分配权重的概念，构建基 于空间增量模型的人口与就业岗位分布模型。利用遗传算法对模型参数进行标定，并通过武汉市江 岸区交通小区数据对模型精度进行验证。结果表明，人口与就业岗位分布预测模型具有一定的可靠 性，能够为城市交通规划模型提供基本的输入数据支持。

关键词： 土地利用；可达性；人口与就业岗位分布；空间增量；遗传算法；武汉市

中图分类号： U491

文献标识码：A

Population and Employment Distribution Forecast Based on Spatial Incremental Model

Ren Zhi1, 2, Zhong Ming1, 2, Li Dashun1, 2, Liu Shaobo1, 2, Zheng Meng3, Ma Xiaofeng1, 2
(1.Intelligent Transport Systems Research Center, Wuhan University of Technology, Wuhan Hubei 430063, China; 2.National Engineering Research Center for Water Transportation Safety, Wuhan University of Technology, Wuhan Hubei 430063, China; 3.Wuhan Transportation Development Strategy Research Institute, Wuhan Hubei 430017, China)

Abstract： How to obtain and update the population and employment distribution data of urban traffic zones is a difficult task facing the current transportation planning. This paper first analyzes the relationship between land use, accessibility, building area and the distribution of urban population and employment. On the basis of space consumption coefficient and considering the influence of accessibility on population and employment distribution, the paper proposes a concept of weight of population and employment incremental distribution and develops a population and employment distribution model based on spatial incremental model. The genetic algorithms is used to calibrate the model parameters, and the accuracy of the model is demonstrated through the data of traffic zones in Jiang'an District, Wuhan. The results show that the population and employment distribution forecasting model is highly reliable and can provide data support for urban transportation planning.

Keywords： land use; accessibility; population and employment distribution; spatial increment; genetic algorithms; Wuhan