UROP Openings

Have a UROP opening you would like to submit?

Please fill out the form.

Submit your UROP opening





11: Urban Studies and Planning

Faculty Supervisor:

Joseph Ferreira

Faculty email:


Apply by:

February 2, 2020



Project Description

We are witnessing revolutionary and exciting changes in the mobility landscape involving infrastructure, technology, and policy. Of particular relevance are emerging modes like autonomous vehicles (AVs) and micro-mobility (like e-scooters), and services like mobility-on-demand (Uber, Lyft, etc.). While their impact on transportation infrastructure and use has received significant attention, we are more interested in understanding how these technologies will shape (or, rather, re-shape) our cities. This particular project is based on our in-house land use-transport interaction (LUTI) simulator named SimMobility, which has three different components. We will focus specifically on the Long-Term (LT) component that models residential location choice, vehicle ownership choice, and job location choice at the individual and household level. Generating synthetic populations for agent-based microsimulations: Agent-based microsimulations are useful in modeling important phenomena, such as tracking the spread of contagion or urban mobility patterns. Since microsimulations are usually very disaggregate, detailed synthetic populations are very useful in representing the scale and heterogeneity of the problem appropriately. This UROP will assist the LT team in creating a synthetic population for Singapore, where ~4 million households and ~6 million individuals are to be generated from a 1% sample collected using a traditional travel survey. We expect this UROP applicant to have taken at least one class in statistics, with at least basic programming experience in R. Students experienced in statistical programming in MATLAB or Python are also eligible, wherein they will be expected to translate their programming skills to R. This UROP will assist the LT team in building on the current method being used, and testing their approach against state-of-the-art methods using machine learning.


(1) Experience in statistical programming using R, MATLAB, or Python (2) Must have taken at least one class in statistics, computation, or optimization (3) Interest in transportation, urban planning and policy (4) The undergraduate applicant must be in their sophomore, junior, or senior year