Investigating machine learning for simulating urban transport patterns: A comparison with traditional macro-models

Abstract

Predicting passenger flow within a city is crucial for intelligent transportation management systems, especially in the context of urban development, post-pandemic policy changes, and infrastructure improvements. Traditional macro models have limitations in accurately capturing the complex structure of real traffic flows, and recent advancements in machine learning offer promising approaches for improving transportation simulations. This research aims to compare the effectiveness of traditional simulation models with a selective machine learning (ML) model for traffic flow prediction in Oslo, Norway. Sensitivity and scenario analyses are conducted to examine the models’ parameters and derive the city’s characteristics. Results substantiate that the traditional Spatial Interaction model (SIM), although interpretable and requiring fewer parameters, has limitations in accurately capturing real flow structures and exhibits greater variability compared to the ML model. Statistical analyses support these findings and raise questions about the validity of the ML model’s results over the SIM. The research highlights the potential of ML models to identify trends in passenger flows and simulate traffic flows in different scenarios related to city development. Overall, the research presents a decision support system for planners and policymakers to predict traffic flow accurately and efficiently. It highlights the benefits and drawbacks of both the traditional SIM and ML models, contributing to the ongoing discussion of the role of machine learning in transportation modeling.