Assessing Physical Environment of TOD Communities around Metro Stations : Using Big Data and Machine Learning

Fang, Wanli ; Liu, Liu ; Zhou, Jianhao

World Bank, Washington, DC

关键词: TRANSIT;    BIG DATA;    MACHINE LEARNING;    URBAN TRANSPORT;    URBAN TRANSIT;   

RP-ID  :  146116

学科分类：社会科学、人文和艺术（综合）

来源: World Bank Open Knowledge Repository

【 摘 要 】

Policy makers and city planningprofessionals who work on transit-oriented development areoften interested in evaluating the quality of physicalenvironment around metro stations. How to carry out thistask comprehensively, effectively and repeatedly, withlimited time and budget? Under the GEF Sustainable CitiesIntegrated Approach Pilot Project (P156507), the task teamhas explored the possibility of utilizing street view photosand machine learning models. The analysis measures physicalenvironment from four aspects, i.e., convenience, comfort,vibrancy and characteristics using 14 subsets of indicators.It covers 201 stations within the 5th Ring Road of Beijingand all indicators are measured for areas within 10-minutewalking distance from the metro stations. The analyticresults can be used to support data-driven andevidence-based city planning and zoning.