Modeling and Analyzing Spatiotemporal Factors Influencing Metro Station Ridership in Taipei: An Approach based on General Estimating Equation

04/02/2019 ∙ by Yuxin He, et al. ∙ 0

Modeling and analyzing metro station ridership is of great importance to passenger flow management and transportation planning operations, and complex as it is affected by multiple factors, including spatial dependencies (distance, network topology), temporal dependencies (e.g., period, trend), and external factors (e.g. land use, social economics). However, existing studies mainly focused on external factors but rarely concerned investigating spatiotemporal influencing factors on metro station ridership. In this paper, we propose a novel data-driven method for metro ridership estimation and influencing factors identification at a refined granular level based on General Estimating Equation (GEE) models. Different from prior research, this study looks at longitudinal station-level metro ridership at different time resolutions. The longitudinal ridership data of Taipei Metro at station-level in the year of 2015 is used to validate the effectiveness of our proposed method. The results demonstrate that the proposed method performs well in a real situation. It implicates that the land use for shopping, bus feeder systems, days since stations were open and transportation hub are significant factors driving ridership at any time resolution. Temporal factors as categorical parameters are also crucial for determining the metro ridership.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 3

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.