liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
City-Agnostic Demand Prediction: A Graph Attention Approach for Urban Transfer Learning
School of Electrical, Electronic and Mechanical Engineering, Faculty of Science and Engineering, University of Bristol, UK.ORCID iD: 0000-0003-0646-284X
Statens väg- och transportforskningsinstitut, Trafikanalys och logistik, TAL.ORCID iD: 0000-0001-6956-7695
Linköping University, Department of Science and Technology, Communications and Transport Systems. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0003-0351-9134
School of Engineering Mathematics and Technology, Faculty of Science and Engineering, University of Bristol, UK.ORCID iD: 0000-0003-2656-363X
Show others and affiliations
2025 (English)In: 2025 IEEE International Smart Cities Conference (ISC2), IEEE , 2025, p. 1-6Conference paper, Published paper (Refereed)
Abstract [en]

Urban transportation planning faces increasing complexity as cities seek to optimize mobility systems without extensive historical data. This paper presents CI-SGNN (City-Invariant Spatial Graph Neural Network), a novel framework for cross-city bike-sharing demand prediction that leverages Point of Interest (POI) distributions and spatial attention mechanisms. Our approach addresses the critical challenge of predicting categorical mobility demand in new urban environments by learning transferable relationships between urban amenities and travel patterns from source cities. The framework integrates OpenStreetMap POI features with GNNs, enabling zero-shot transfer learning across diverse metropolitan areas. We formulate demand prediction as a multi-class classification problem, categorizing origin-destination pairs into five demand levels. Experimental validation using real CitiBike data from Manhattan and Washington DC demonstrates superior performance, achieving 72.4% accuracy, which overperforms state-of-the-art base-lines. The attention-based spatial aggregation mechanism effectively captures inter-zone dependencies. Our results demonstrate successful zero-shot adaptation capabilities, enabling practical deployment for bike-sharing infrastructure planning in cities lacking historical mobility data using only publicly available urban features. 

Place, publisher, year, edition, pages
IEEE , 2025. p. 1-6
Series
IEEE ... International Smart Cities Conference, ISSN 2687-8860
Keywords [en]
Smart City, Micro-mobility planning, Demand prediction, Machine Learning, Graph Neural Networks
National Category
Transport Systems and Logistics
Identifiers
URN: urn:nbn:se:liu:diva-224118DOI: 10.1109/isc266238.2025.11293298Scopus ID: 2-s2.0-105031899834ISBN: 9798331557737 (electronic)OAI: oai:DiVA.org:liu-224118DiVA, id: diva2:2060900
Conference
2025 IEEE International Smart Cities Conference (ISC2), Patras, Greece, October 06-09, 2025.
Projects
ELABORATOR
Funder
EU, Horizon Europe, 101103772Available from: 2026-05-19 Created: 2026-05-19 Last updated: 2026-05-19

Open Access in DiVA

fulltext(13640 kB)192 downloads
File information
File name FULLTEXT01.pdfFile size 13640 kBChecksum SHA-512
446944b77ab4a1b16540b09c1bbc511af9164d24badd9e0cdc2d6933341ada4388f0b2ddf47e452931efe7b0c1074d8d62fed12814f69e00f154ff2f9d70987f
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Klar, RobertAngelakis, Vangelis

Search in DiVA

By author/editor
Erdol, HakanKlar, RobertAngelakis, VangelisPope, JamesPiechocki, RobertTryfonas, TheoOikonomou, George
By organisation
Communications and Transport SystemsFaculty of Science & Engineering
Transport Systems and Logistics

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 155 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf