Detailed knowledge of service utilisation and passenger load profiles are the basis for the design, operation, and adjustment of a public transport service. The advancement in sensing technologies enable transit operators to monitor the variabilities in passenger flows continuously and consistently. There is a growing body of literature on using supervised learning models with direct passenger counts from historical observations. However, the incomplete, inaccurate, and biased data from automatic sensors pose a challenge in this process. This paper proposes novel supervised learning models to estimate public transport service load profile onboard, based on 1) limited data collected on a subset of service vehicles by automatic passenger counting (APC) systems, and 2) fare data collected by automated fare collection (AFC) systems, with the specific consideration that the developed models can be transferred across different routes. This is motivated by the commonly “limited coverage” of automated passenger counter devices on service vehicles. We introduce an array of new models and a superior segment-based model which demonstrates remarkable improvement in model transferability and accuracy. The proposed methodology uses separate methods in different segments of a transit line.
The proposed models are applied to three tram lines in Melbourne, Australia, where different types of shortcomings exist in the automated data. The test results show that the proposed models can be transferred and applied to other transit route without historical observations. This would allow transit operators to reduce the number of required devices and monitor service utilization more cost-efficiently, especially in public transport networks where AFC coverage is usually incomplete and negatively skewed. The information on service utilization will not only help operators to accommodate the variability in passenger demand, but also assist passengers in journey planning to avoid service overcrowding.