LLMs & Knowledge Graphs for Scientific Discovery and DMDU

We explore how Large Language Models (LLMs) and Knowledge Graphs (KGs) can advance transport research and planning. Our work focuses on scientific discovery, causal reasoning, and adaptive planning under deep uncertainties, enabling new ways to understand mobility behavior and design policy interventions.
Key topics: travel behavior modeling with LLMs, transdisciplinary knowledge graphs, adaptive planning under deep uncertainty.

Digital Twins for Transport Systems

We develop Digital Twin (DT) frameworks to enable real-time monitoring, forecasting, and control of transport networks. By integrating IoT sensing, simulation, and reinforcement learning, our research creates adaptive and scalable solutions for traffic management.
Key topics: network-level traffic control, multi-agent reinforcement learning, IoT-enabled simulation.

Public Transport & Railway Data Analytics

We apply advanced data-driven methods to improve the performance, reliability, and sustainability of public transport and railway systems. Our research addresses both passenger experience and operational efficiency, with a focus on developing robust, evidence-based strategies for transit planning and management.
Key topics: service reliability and regularity, crowding analysis and management, operations and timetabling optimization, multimodal coordination, and planning for electrified transit fleets.