Embedding spatial context in urban traffic forecasting with contrastive pre-training
This work addresses the problem of enhancing traffic prediction accuracy for urban planners and engineers by integrating spatial context, though it is incremental as it builds on existing GNN-based methods.
The paper tackles urban traffic forecasting by incorporating non-traffic spatial context data, such as road geometry from OpenStreetMap, through a novel traffic quotient graph and contrastive pre-training, resulting in improved generalization and performance without additional traffic data.
Urban traffic forecasting is a commonly encountered problem, with wide-ranging applications in fields such as urban planning, civil engineering and transport. In this paper, we study the enhancement of traffic forecasting with pre-training, focusing on spatio-temporal graph methods. While various machine learning methods to solve traffic forecasting problems have been explored and extensively studied, there is a gap of a more contextual approach: studying how relevant non-traffic data can improve prediction performance on traffic forecasting problems. We call this data spatial context. We introduce a novel method of combining road and traffic information through the notion of a traffic quotient graph, a quotient graph formed from road geometry and traffic sensors. We also define a way to encode this relationship in the form of a geometric encoder, pre-trained using contrastive learning methods and enhanced with OpenStreetMap data. We introduce and discuss ways to integrate this geometric encoder with existing graph neural network (GNN)-based traffic forecasting models, using a contrastive pre-training paradigm. We demonstrate the potential for this hybrid model to improve generalisation and performance with zero additional traffic data. Code for this paper is available at https://github.com/mattchrlw/forecasting-on-new-roads.