Track: Modeling and Simulation

Abstract

Predicting metro ridership is an essential requirement for efficient metro operation and management.  The dependence of Metro ridership on the land-use densities is extremely logical and entails a need for a model that predicts the Metro ridership using land use densities. The objective of this research study is to develop a model to predict the metro station ridership utilizing the land use densities in the vicinity of metro stations. A Support Vector Machine (SVM) model was developed as a classifier in order to predict ridership patterns. The ridership data was obtained from Qatar Rail, and the land use data were obtained from the Ministry of Municipality and Environment (MME), State of Qatar. The land use densities in the catchment area of 800m around the metro stations have been considered in this study. The nonlinear relationship between the metro ridership and land use densities has been captured through the SVM model. The resultant performance of models prediction showed a rational accuracy in which the variance of predicted ridership and actual data didn’t exceed  0.14,  the proposed prediction model can be utilized by both Urban and transport planners in their processes to plan the land use around metro stations and predict the transit demand from those plans and achieve the optimal use of the transit system i.e. Transit-Oriented Developments (TOD).