Yelu’s PhD will focus on generating synthetic mobility trajectories for privacy-preserving data sharing. 

The growth in the availability of fine-grained mobility data has spurred high-impact research findings into the nature of human mobility. There remains significant potential for enhanced understanding of mobility behaviour to help improve the reliability and sustainability of urban transportation systems.  

Despite major safeguards in place around the storage and use of fine-grained mobility data, there remain concerns about the risk to individual privacy, and questions about the continued willingness of the public to permit data for use in research.   

Yelu’s PhD project will seek to advance the state-of-the-art in synthetic trajectory production through the development of methods that better capture spatial, temporal, and contextual heterogeneity.  

She will seek to encode features such as travel mode choice, gender, age, and co-presence in our synthetic models. Furthermore, she will assess how we can account for, or integrate, non-recurrent events, such as travel disruptions, holidays, and weather, in realistically replicating mobility trajectories.