Inferring Social Functions Available in the Metro Station Area from Passengers’ Staying Activities in Smart Card Data

Abstract

The function of a metro station area is vital for city planners to consider when establishing a context-aware Transit-Oriented Development policy around the station area. However, the functions of metro station areas are hard to infer using the static land use distribution and other traditional survey datasets. In this paper, we propose a method to infer the functions occurring around the metro station catchment areas according to the patterns of staying activities derived from smart card data. We first define the staying activities by the spatial and temporal constraints of the two consecutive alighting and boarding records from the individual travel profile. Then we cluster and label the whole staying activities by considering the features of duration, frequency, and start time. By analyzing the percentage of different types of aggregated activities happening around each metro station, we cluster and explore the functions of the metro station area. Taking Wuhan as a case study, we analyze the results of Wuhan metro systems and discuss the similarities and differences between the functions and the land use distribution around the station area. The results show that although there exist some agreements, there is also a gap between the human activities and the land uses around the station area. These findings could give us deeper insight into how people act around the stations by metro systems, which will ultimately benefit the urban planning and policy development.

Identifying Building Functions from the Spatiotemporal Population Density and the Interactions of People among Buildings

“…In recent years, multisource spatiotemporal big data, such as mobile phone data, taxi trajectory data, and social media check-in data, have emerged. These data record people's spatiotemporal activity position information and have shown unique advantages and potential in researching human activities, urban functional regions, regional structures and land uses [16][17][18][19][20][21][22]. Some scholars have also tried to use these human time-series position data to infer the building functions.…”

A multi‐modal transportation data‐driven approach to identify urban functional zones: An exploration based on Hangzhou City, China

“…The bicycle rental records from 2,370 stations were sampled hourly from 06:00 on November 11 to 05:00 on November 21, 2017, and the data included the number of available bicycles and the number of free slots for each station. Compared to bus and metro systems (Zhou, Fang, Zhan, Huang, & Fu, ), the distribution of bicycle stations has relatively complete coverage over the core urban area (see Figure c). In addition, the public bicycle‐sharing system has been operational for almost 10 years, and the maximum usage so far has reached 473,000 times per day, showing that it has been vital for daily travel choice by citizens.…”

Detecting and understanding urban changes through decomposing the numbers of visitors’ arrivals using human mobility data

“…Individual travel patterns have been used by several studies for inferring the respective trip purpose [9,10,[13][14][15][16]. For instance, Alexander et al [9] infer trip purpose from call detail records (CDRs) which are collected through the use of mobile phones that contain time-stamped geo-coordinates.…”