Identifying primary public transit corridors using multi-source big transit data

ABSTRACT

Effective public transit planning needs to address realistic travel demands, which can be illustrated by corridors across major residential areas and activity centers. It is vital to identify public transit corridors that contain the most significant transit travel demand patterns. We propose a two-stage approach to discover primary public transit corridors at high spatio-temporal resolutions using massive real-world smart card and bus trajectory data, which manifest rich transit demand patterns over space and time. The first stage was to reconstruct chained trips for individual passengers using multi-source massive public transit data. In the second stage, a shared-flow clustering algorithm was developed to identify public transit corridors based on reconstructed individual transit trips. The proposed approach was evaluated using transit data collected in Shenzhen, China. Experimental results demonstrated that the proposed approach is a practical tool for extracting time-varying corridors for many potential applications, such as transit planning and management.

KEYWORDS:

• Transit corridors
• smart card data
• trajectory data
• clustering
• trip

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by the National Natural Science Foundation of China [No. 41871308]; National Key Research and Development Program of China [No. 2017YFB0503502]; Basic Scientific Research Fund Program of Chinese Academy of Surveying and Mapping [No. 7771820].

Notes on contributors

Tong Zhang

Tong Zhang received the M.Eng degree in Cartography and GIS from Wuhan University, China, in 2003, and the Doctoral degree in Geography from San Diego State University and University of California, Santa Barbara in 2007. He is currently a professor at State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan. His current research topics include big spatio-temporal data analytics, high performance geocomputation, and geospatial optimization.

Yicong Li

Yicong Li is currently a M.S. student in GIScience at LIESMARS, Wuhan University. He obtained the B.S degree in Remote Sensing from Wuhan University in 2017. His research interests include GIS-T and machine learning.

Hui Yang

Hui Yang is currently a M.S. student in GIScience at LIESMARS, Wuhan University. Mr. Yang received the bachelar's degree in GIS from Chinese University of Geosciences (Beijing) in 2017. His research interests include spatio-temporal data mining, transportation, and machine learning.

Chenrong Cui

Chenrong Cui is a M.S. student in GIScience at LIESMARS, Wuhan University. She received the bachelar's degree in Surveying and Mapping from Henan Polytechnic University in 2016. Her research interests include spatio-temporal data mining and geovisualization.

Jing Li

Jing Li received MS in Earth System Science from George Mason University, USA in 2009 and the Ph.D. in Earth System and Geoinformation Science from the same university in 2012. She is currently an Associate Professor in the Department of Geography and the Environment at University of Denver, USA. Her research interests are high performance computing, spatiotemporal data modeling, and geovisualization.

Qinghua Qiao

Qinghua Qiao is an Associate Researcher at Chinese Academy of Surveying and Mapping (CASM). In 2007, Dr. Qiao received the Ph.D. degree in GIScience from Wuhan University before he joined CASM. Dr. Qiao has been working on spatial database, GIS-T, and GIS applications for the past 10 years.