Neural network approaches for forecasting short-term on-road public transport passenger demands

On-road public transport plays an essential role in urban mobility and in meeting people’s needs for travel. Service reliability and punctuality are important factors in encouraging more people to use these forms of transport and improving passenger user experiences in a modern world where passengers expect higher levels of service availability and reliability. On-road public transport operators can improve services when they have access to reliable estimates of passenger demands, which helps them to adjust timetables for each service route efficiently based on average passenger demands at public transport stops or on a service route at a specific time. This chapter presents an overview of the extensive research performed in the recent decade on AI-based passenger demand forecasting for public transport systems. The chapter also provides insights into the potential of AI-based prediction, and how it has been shown to achieve high forecasting accuracy exceeding 90% using real-world datasets.