Spatio-Temporal Point Processes with Attention for Traffic Congestion Event Modeling
This work addresses traffic congestion prediction for urban planning and management, representing an incremental improvement with domain-specific applications.
The authors tackled traffic congestion event modeling by developing a framework that combines traffic sensor data with police reports to capture triggering effects from current congestion and traffic incidents. Their approach demonstrated superior performance compared to state-of-the-art methods on both synthetic and real data.
We present a novel framework for modeling traffic congestion events over road networks. Using multi-modal data by combining count data from traffic sensors with police reports that report traffic incidents, we aim to capture two types of triggering effect for congestion events. Current traffic congestion at one location may cause future congestion over the road network, and traffic incidents may cause spread traffic congestion. To model the non-homogeneous temporal dependence of the event on the past, we use a novel attention-based mechanism based on neural networks embedding for point processes. To incorporate the directional spatial dependence induced by the road network, we adapt the "tail-up" model from the context of spatial statistics to the traffic network setting. We demonstrate our approach's superior performance compared to the state-of-the-art methods for both synthetic and real data.