AI could revolutionize Dhaka’s urban transportation system

AI Could Help Transform Dhaka’s Traffic Management and Urban Transport

Artificial intelligence (AI) could provide a new approach to Dhaka’s persistent traffic congestion by making urban transport planning more data-driven, responsive and focused on commuters’ needs, according to Chinese transport researcher Dr Qian Li.

An associate professor at Tongji University in Shanghai, Dr Li recently presented his research on using large language models (LLMs) for urban transport management at seminars at North South University and the University of Dhaka.

His work explores how AI and big data can complement traditional traffic engineering to create smarter, more user-centred mobility systems.

At the core of his research is a four-layer framework—Data + Knowledge Graph (KG) + Model + Task—which combines mobility data, specialised knowledge, AI models and specific transport tasks to improve planning and decision-making.

While conventional traffic engineering focuses largely on vehicle counts, traffic signals and road design, Dr Li’s approach uses big data and AI to analyse travel behaviour and respond more effectively to changing passenger demand.

A key area of his research is urban mobility analysis using mobile phone location and movement data. Such data can reveal daily travel patterns and help authorities make more informed decisions about transport infrastructure and services.

His research also focuses on sustainable mobility, including electric bus management, carbon-emission monitoring and low-carbon transport planning. He has additionally examined blockchain technology as a tool to improve transparency in hazardous-goods transportation and coordination among agencies.

Dr Li’s work has been applied to transport challenges in Shanghai and other major cities. One notable application involves using citizen hotline data to identify transport problems and improve public bus services.

He has also developed a knowledge-enhanced AI system designed to reduce inaccuracies and fabricated responses sometimes produced by general-purpose LLMs. The system integrates textbooks, government policies and transport research into a knowledge graph and uses retrieval-augmented generation to deliver more reliable information on specific bus routes and express services.

During his Dhaka seminars, Dr Li highlighted the importance of collaboration between universities, research institutions and public and private technology companies in developing smart transport systems.

For Dhaka, such an AI-based framework could potentially support traffic management, bus route rationalisation and better integration between feeder buses and the metro rail network.

By combining mobility data with feedback from commuters, AI could help transport planners develop more targeted, efficient and cost-effective solutions to the capital’s chronic congestion.

Dr Li holds a PhD in Civil and Environmental Engineering from Rutgers University in the United States and previously worked as a postdoctoral research associate at The Hong Kong Polytechnic University. He joined Tongji University in 2014 and has conducted research on traffic engineering, transport planning, big data and artificial intelligence.

According to his ResearchGate profile, he has published more than 52 research papers, received over 855 citations and recorded more than 10,000 reads.