Analysing the influence of electric bike types on route preferences in urban cycling environments: A GPS data-driven approach
Manya Singh,
Pavlos Tafidis and
Francesco Pilla
Journal of Transport Geography, 2025, vol. 128, issue C
Abstract:
There is a notable trend towards an increase in e-bike adoption as compared to car ownership in urban European cities. This calls for cities to rethink their transportation and infrastructure strategies to better accommodate the diverse needs of all cyclists. This paper focuses on Dublin, where the Bike Library (i.e., a community-based bike-borrowing scheme) reported over 8400 trips, using different types of e-bikes: folding, cargo, and standard, over six months. The objective is to examine route preferences by analysing how cyclists interact with infrastructure such as cycle lanes, segregated cycle lanes, and bus lanes, which could be influenced by factors like travel distance, trip duration, and elevation differences. Variations in bike infrastructure usage were measured using statistical t-tests on the collected GPS data based on e-bike type. The route features of trips taken by each cyclist were further examined to find the shortest alternatives to the actual route. The combination of features of the observed trips and shortest alternative trips were fit to logistic regression and random forest models forming a binary classification task: deciding whether a trip is favourable or not. These models help us understand what features are desirable to a cyclist at the cost of added distance in their trip. It also shows features that are not desirable such as shared use lanes and surface change lanes. The resulting models were able to predict route choice accurately up to 65 % on unseen data while also highlighting the most important features in making route choices. Interestingly, the type of e-bike is the most important feature in making a route choice. These findings can help urban planners to create more cyclist-friendly routes in Dublin and increase cycling interest in the city.
Keywords: GPS data; E-bike cycling behaviour; Urban cycling infrastructure usage; Route choice modelling; Random forest; Logistic regression (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:
Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0966692325002030
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:eee:jotrge:v:128:y:2025:i:c:s0966692325002030
DOI: 10.1016/j.jtrangeo.2025.104312
Access Statistics for this article
Journal of Transport Geography is currently edited by Frank Witlox
More articles in Journal of Transport Geography from Elsevier
Bibliographic data for series maintained by Catherine Liu ().