Research

Transportation research powered by optimization and machine learning.

MoS Lab studies how models, algorithms, and data can help transportation systems operate more efficiently, intelligently, and sustainably under uncertainty, disruption, and rapid urban change.

Featured Research

Schematic of the individual path recommendation problem on a disrupted rail and bus network (Figure 1, Transportation Science)

Public Transit Resilience

Individual path recommendation under transit disruptions

Models passenger behavior uncertainty and recommends resilient paths during service disruptions.

Commuting patterns in Beijing, Munich, and Singapore before and after housing exchange (Figure 2, Nature Sustainability)

Sustainable Urban Systems

Housing exchange to reduce commuting emissions

Uses household-level housing exchange strategies to reduce excess commuting emissions.

Pair-wise attention-based pointer neural network architecture (Figure 2, Transportation Research Part E)

Mobility AI

Last-mile delivery route prediction

A pair-wise attention-based pointer neural network that predicts drivers' route trajectories in last-mile delivery.

Physical network and time-space hypernetwork representation (Figure 1, Transportation Science)

Public Transit Resilience

Ex post path choice estimation

Estimates urban rail passenger path choices from smart card data via an aggregated time-space hypernetwork.

Research Areas

Transportation System Resilience

When incidents disrupt transportation systems, we study how efficient optimization and machine learning algorithms can adjust operations, guide passengers, and help systems recover quickly. Topics include incident-aware passenger behavior inference, robust path recommendation, network performance modeling, and resilient operations control.

AI for Transportation

We apply AI to public transit, shared mobility, and supply-chain logistics, including reinforcement-learning-based real-time decisions, time-series foundation models, transportation management agents, ETA prediction, and last-mile delivery route prediction.

Travel Behavior & Demand Modeling

We combine policy analysis, surveys, econometric models, smart card data, license plate recognition data, machine learning, and optimization to improve traditional behavioral and demand models.

Sustainable Urban Systems

We study commuting carbon emissions, public health risk, housing mobility, and urban cyber-physical-social system resilience, placing transportation in broader sustainability and interdisciplinary policy-evaluation frameworks.