With increasingly advanced and widespread data capture technologies and applications, massive multi-source traffic data such as mobile communication data, GPS data, AFC card data, Wi-Fi probe data, etc., provides valuable data resources for public transport operations. The recent idea of using big data technology to assist public transport operations can help to achieve passenger analysis, passenger intelligent control, and train operation systems.

However, we still face some challenges in urban transit big data analysis, mining, and application. For example, how to extract individual passenger travel information from AFC data; how to combine multi-source data to predict high-precision passenger flow in complex scenarios; how to dynamically trace individual passengers on their whole trip; and how to optimize passenger flow control strategies using big data methods.

This Special Issue aims to provide a platform for researchers and practitioners to exchange ideas about big data applications in a public transport operation. Original research and review articles will be considered. All aspects of travel behaviour mining, demand analysis, state estimation, and passenger flow or train control are of interest.

Potential topics include but are not limited to the following:

• Trip purpose mining from big data
• Passenger choice behaviour analysis based on big data
• Real-time passenger flow prediction
• Passenger flow prediction under special events
• Train delay prediction
• Passenger delay estimation
• Big data in passenger assignment
• Time and space evolution of passenger flow based on big data
• Intelligent passenger flow control
• Data-driven passenger flow risk assessment of public transport
• Capacity estimation analysis of public transport