Extracting spatiotemporal commuting patterns from public transit data

Trivik Verma, Mikhail Sirenko, Itto Kornecki, Scott W. Cunningham, Nuno A. M. Araujo

Research output: Contribution to journalArticlepeer-review


Public transit networks in cities are crucial in addressing the transforming mobility needs of citizens for work, services and leisure. The rapid changes in urban demographics pose several challenges for the efficient management of transit services. To forecast transit demand, planners often resort to sociological investigations, modelling or population data that are either difficult to obtain, inaccurate or outdated. How can we then estimate the variable demand for mobility? We propose a simple method to identify the spatiotemporal demand for public transit in a city. Using a Gaussian mixture model, we decompose empirical ridership data into a set of temporal demand profiles representative of ridership over any given day. A case of million daily transit traces of the primary mode of underground services from the Greater London region reveals distinct commuting profiles. We find that a weighted mixture of these profiles can generate any station traffic remarkably well, uncovering spatially concentric clusters of mobility needs. Our results also suggest that heavily used stations that exhibit mixed-use commuting patterns are generally located in the cluster of the central business district and stations away from the centre of the city are largely single use residential areas. Overall, identifying mixed temporal and spatial use of stations diverging from macro mobility patterns in public transit indicates that our approach may be useful in a detailed understanding of integrated transit planning for heterogeneous needs of travellers.
Original languageEnglish
Article number100004
Number of pages10
JournalJournal of Urban Mobility
Early online date3 Aug 2021
Publication statusE-pub ahead of print - 3 Aug 2021


  • smart card data
  • mixture models
  • clustering
  • demand forecasting
  • public transit


Dive into the research topics of 'Extracting spatiotemporal commuting patterns from public transit data'. Together they form a unique fingerprint.

Cite this