Our overarching goal is to explore and understand the complexity of urban mobility systems on the spatio-temporal scale. To do so, we use and develop novel geospatial analytics tools to unravel the relevant socio-economic phenomenons of freedom.

Questions of interest include: (i), How does the citizen move inside the city and how is this related to the complex configuration of urban built environment? (ii), What is the recurrent mobility pattern seen in correlated urban systems? Is this a spatio-temporal sensitive state? What is the mechanism of dissipation in that state? (iii), Why is the transition pattern in urban mobility systems so predictable?

Topic I: Collective

We explore and model how people move collectively in urban space to act more intelligently than any individual person or group could do.

Benefit equilibrium

Understanding operation behaviors of taxicabs in cities by matrix factorization

Route optimization

Quantifying tourist behavior patterns by travel motifs and geo-tagged photos from Flickr

Preferential visitation

How urban places are visited by social groups? Evidence from matrix factorization on mobile phone data

Distance deterrence

Understanding intra-urban trip patterns from taxi trajectory data

Topic II: Complexity

We apply methods at the intersection of complexity science and big data analytics to reveal hidden regularities in the organisation of cities.


Hub locations

Measuring hub locations in time-evolving spatial interaction networks based on explicit spatiotemporal coupling and group centrality

Topic III: Computation

We acquise, integrate, and analyze big and heterogeneous data generated by a diversity of sensors to tackle the major issues that cities face.

Air pollution

Predicting vehicular emissions in high spatial resolution using pervasively measured transportation data and microscopic emissions mode
Escaping from pollution - The effect of air quality on inter-city population mobility in China

Traffic congestion

Modeling spatio-temporal evolution of urban crowd flows
A graph convolutional network model for evaluating potential congestion spots based on local urban built environments

Land use

A framework for mixed-use decomposition based on temporal activity signatures extracted from big geo-data
Incorporating spatial interaction patterns in classifying and understanding urban land use
An ensemble learning approach for urban land use mapping based on remote sensing imagery and social sensing data

Urban expansion

Topic IV: Collaboration

We serve as a research hub and build analytical platforms for collaborative action and innovation to address complex societal problems.

Urban perception

Validating activity, time and space diversity as essential components of urban vitality

Planning assistance

Explainable AI