I am an Associate Professor and William Dawson Scholar in the Department of Civil Engineering at McGill University, where I lead the Smart Transportation Lab. I received my Ph.D. in Civil Engineering (Transportation) from the National University of Singapore and my B.Eng. in Civil Engineering from Tsinghua University. During my Ph.D., I worked in the Mobility and Transportation Planning module of the Future Cities Laboratory, Singapore-ETH Centre. Prior to joining McGill in 2018, I was a Postdoctoral Associate at the MIT Media Lab.

My research develops statistical and machine learning methods for transportation systems that are only partially observed—incomplete passenger counts, sparse trajectories, censored demand—and for decisions that change what will be observed next. It connects three areas that are often treated separately: inference about latent transportation systems (inverse problems such as origin–destination estimation and passenger flow assignment), structured uncertainty quantification (Bayesian spatiotemporal and low-rank tensor models, probabilistic forecasting with correlated errors), and operational decision-making under uncertainty (public transit operations, Bayesian optimization, surrogate-based optimization). My group is also exploring generative AI and large language model agents for mobility reasoning, synthetic travel data and population synthesis. See Publications for representative work by theme.

I serve as Managing Editor of Artificial Intelligence for Transportation, Area Editor of Transportation Research Part C, and Associate Editor of Transportation Science. My research has been recognized by the Best Paper Award of the TRB Standing Committee on Statistical and Econometric Methods (2024), McGill’s Christophe Pierre Award for Research Excellence (2023), and the Faculty of Engineering Class of 1944 Outstanding Teaching Award (2022). My work has been featured in Scientific American, WIRED, MIT Technology Review and New Scientist.

For Prospective Students/Postdocs

• I am looking for 1–2 PhD students for Fall 2027 (and Winter 2028) who are excited about statistics, machine learning and optimization for transportation and mobility systems. If you are interested, please apply through the McGill uApply system and send me an email with your CV and transcripts, using “Prospective PhD student [Your name]” as the subject. Due to the large volume of emails, I apologize for not being able to reply to every inquiry.
• See more info about Civil Engineering @ McGill University.
• If you have a strong record in mathematics/statistics/machine learning, you are encouraged to apply for the IVADO graduate student scholarship.
• Postdocs or final-year PhD students with a strong background in statistics, machine learning or operations research (and an interest in transportation applications, e.g., spatiotemporal modeling, probabilistic forecasting, generative models for urban activity) are strongly encouraged to get in touch. I am happy to support competitive candidates for external fellowships such as IVADO, NSERC Banting, NSERC Postdoctoral Fellowship, FRQNT and Mitacs Elevate.
• Scholarship opportunities:
• for PhD: McGill MEDA, McGill MEITA, FRQNT doctoral scholarship (B2X), CSC, Quebec-China Scholarship, PBEEE Level 1 Graduate, Quebec DFW, IVADO;
• for Postdoc: Mitacs Elevate, NSERC Banting (best in Canada), NSERC Postdoctoral Fellowship, PBEEE Level 2 Postdoc, IVADO, CSC;
• for Undergraduate: Mitacs Globalink/international, NSERC USRA, McGill SURE.

Research Interests

• Bayesian statistics and uncertainty quantification for transportation systems
• Spatiotemporal modeling, low-rank tensor learning and Gaussian processes
• Probabilistic forecasting of traffic, demand and travel time
• Inverse problems in transportation: origin–destination estimation, passenger flow assignment, unmet demand
• Human mobility, travel behavior and choice modeling
• Population synthesis and generative AI for mobility (synthetic travel data, LLM agents)
• Public transport operations and planning
• Decision-making under uncertainty: Bayesian optimization, surrogate-based and stochastic optimization
• Driver behavior and stochastic traffic simulation
• Shared and active mobility