Research.

Developing analytical tools and producing findings directly useful for transport policy and urban planning, with a focus on mobility inequality and spatial data science.

I use spatial data science and computational methods to understand mobility inequality in cities: who gets access to good transport, which neighbourhoods are systematically underserved, and what new forms of data can reveal about the people and places that conventional transport analysis leaves behind.

My work spans travel behaviour analysis, shared and emerging mobility systems, and the development of computational methods for transport applications. I apply methods ranging from graph-based network analysis and geospatial machine learning to large language models, working with diverse data sources including GPS tracking data, shared mobility records, and user-generated geographic content.

A particular focus is transport equity: understanding how infrastructure, services, and planning decisions shape mobility outcomes differently across social groups and places.

Graph-based network analysis
Geospatial machine learning
Spatiotemporal trajectory analysis
Large language models
Geodemographic classification
GPS tracking data
Shared mobility records
Smart card / transit data
01

Transport Equity & Mobility Inequality

Understanding how urban transport systems produce and reproduce spatial inequality. This includes who is systematically excluded from mobility, which places are underserved, and what high-resolution data can reveal about the gap between transport provision and genuine need across diverse social groups and communities.

I am particularly interested in developing geodemographic and spatial analytical approaches that reveal the distributional consequences of transport investment decisions and emerging service patterns, including work on cycling equity, ageing populations, and differential access across communities.

SPATIAL INEQUALITY GEODEMOGRAPHICS CYCLING EQUITY AGEING TRANSPORT ACCESS
02

Spatial Data Science & Computational Methods

Developing and applying computational methods, including graph-based network analysis, geospatial machine learning, spatiotemporal trajectory analysis, and large language models, to extract insight from complex, multi-modal urban and transport datasets such as GPS traces, user-generated geographic content, and unstructured spatial text.

A particular focus is how graph-theoretic approaches can model structural properties of transport networks and flow patterns, enabling better understanding of connectivity, resilience, and the cascading effects of disruption.

GRAPH ANALYSIS MACHINE LEARNING TRAJECTORY MINING NETWORK RESILIENCE SPATIAL COMPUTATION
03

Emerging & Sustainable Transport Systems

Examining adoption, behaviour, and well-being outcomes across new and evolving forms of urban mobility, with a focus on who benefits from emerging transport services and how inclusive design can support broader sustainability transitions in cities.

Much of this work focuses on shared micromobility, including bike-sharing systems, dockless bikes, and e-scooters, examining their spatial reach, user profiles, trip purposes, and effects on well-being.

BIKE SHARING E-SCOOTERS WELL-BEING MODE SHIFT LAST-MILE

Research projects.

Past and active funded projects and collaborations.