ITSC 2024 Paper Abstract

Paper ThBT14.6

Pollock, Sam (University of Calgary), Demissie, Merkebe Getachew (University of Calgary, Calgary, Canada), Kattan, Lina (University of Calgary)

Modelling Link-Level Shared Micromobility Demand: Regression and Neural Network Approaches

Scheduled for presentation during the Poster Session "Modeling and Optimization of Mobility and Transport Systems " (ThBT14), Thursday, September 26, 2024, 14:30−16:30, Foyer

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on December 26, 2024

Keywords Other Theories, Applications, and Technologies, Data Mining and Data Analysis

Abstract

Shared micromobility is a relatively new transportation mode that has the potential to replace short-distance motor vehicle trips. To encourage shared micromobility ridership, transportation practitioners must understand the determinants of micromobility demand. Previous research has examined micromobility demand on a zonal basis; however, the decision to build micromobility and active transportation infrastructure happens on a link basis. This study presents a linear regression model, a spatial lag model, and a neural network that are used to examine the impact of the built environment on micromobility demand in Calgary, Canada using micromobility data from 2019-2023. Point of interest density was found to be a more important predictor of micromobility demand than road classification or active transportation infrastructure. Urban boulevards are the road classification most associated with increased demand. Active transportation facilities, especially those that separate users from motor vehicles, are also associated with higher micromobility volumes. Of the three models, the spatial lag model had the most predictive power because it accounted for spatial relationships. This demonstrates the importance of accounting for spatial lag and error when evaluating micromobility demand at a link level. The results of this study may provide insight for future micromobility and active transportation infrastructure developments.