Traffic prediction and road space optimization for the integration of dockless bike-sharing and subway

Document Type

Journal Article

Publication Date

2025

Subject Area

place - asia, place - urban, mode - subway/metro, mode - bike, planning - integration, planning - methods, planning - travel demand management, policy - sustainable

Keywords

Subway, dockless bike-sharing (DBS), sustainability

Abstract

The integration of dockless bike-sharing (DBS) and subway is an effective measure to promote sustainable urban transportation. However, inaccurate traffic prediction and unreasonable road space allocation have brought a severe imbalance between supply and demand, significantly restricting its application. To address these issues, this study first employs machine learning to establish a traffic prediction model at the origin–destination level. Then, we propose a road space optimization method based on multi-source geospatial big data, aiming to compress motorized lanes and increase cycling space. Results from the Beijing case indicate: (1) The XGBoost model achieves the best prediction accuracy, with an R2 of 0.68 ± 0.04. (2) The optimization method can accurately identify high-priority areas, and compressing each motorized lane only by 0–0.41 m can achieve reasonable allocation and still meet official standards. This study will assist policymakers in identifying demand and adjusting infrastructure within the DBS-subway integration scenario, ultimately achieving sustainable transportation systems.

Rights

Permission to publish the abstract has been given by Elsevier, copyright remains with them.

Comments

Sustainable Cities and Society Home Page:

http://www.sciencedirect.com/science/journal/22106707

Link to Full Text

Share

COinS