Enhancing Dublin’s Bike-Sharing Network: Leveraging Deep Learning for Growth and Efficiency

Bernal Gomez, Valentina (2025) Enhancing Dublin’s Bike-Sharing Network: Leveraging Deep Learning for Growth and Efficiency. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (4MB) | Preview
Preview	PDF (Configuration Manual) Download (4MB) | Preview

Abstract

The population around the world is growing every year, which makes more people move into main cities, for different reasons such as work, studies or tourism, and traffic is getting worse, as most people use cars or public transport. Bicycles are becoming a healthy and sustainable option to reduce congestion and move faster inside the cities. For this reason, bike-sharing services have been introduce in large cities to encourage people to use bikes and reduce traffic conditions. However, when focusing in planning and traditional approaches there are a lack of use of spatial and temporal analysis and fail to address class imbalance in the data use. This research aims to improve and help with the expansion of Dublin’s bike-sharing network by developing a deep learning based methodology that combines clustering techniques, spatio-temporal analysis, and predictive modeling using Graph Neural Networks, furthermore, the study includes an analysis of the network infrastructure and provides strategic suggestions for system improvement. Multiple variations were tested and the best performance was achieved by a GCN model with focal loss and no leakage information, reaching an accuracy of 0.986 and a F1-score of 0.971. The findings demonstrate the potential of integrating deep learning models into urban planning to improve the network and the efficiency of the system.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Rustam, Furqan UNSPECIFIED
Uncontrolled Keywords:	Clustering Techniques; Predictive Modeling; Spatio-temporal Analysis; Bike-Sharing Systems
Subjects:	D History General and Old World > DA Great Britain > Ireland > Dublin Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HE Transportation and Communications > Urban Transportation
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	30 Jun 2026 17:04
Last Modified:	30 Jun 2026 17:04
URI:	https://norma.ncirl.ie/id/eprint/9411

Actions (login required)

View Item