TimeBird: Context-Aware Graph Convolution Network for Traffic Incident Duration Prediction

TL;DR: Wang et al. as discussed by the authors proposed a context-aware spatio-temporal graph convolution framework, named TimeBird, to estimate the duration time of traffic incidents and designed a contextaware attention mechanism to adaptively learn the heterogeneous traffic features for incident duration prediction.

Abstract: Estimating the traffic incident duration is of great importance to traffic control, traffic navigation, and transportation safety. However, the complex road network topology and dynamic traffic conditions make it challenging. In this paper, we propose a context-aware spatio-temporal graph convolution framework, named TimeBird, to estimate the duration time of traffic incidents. Specifically, we build the dynamic weighted adjacency matrix and traffic incident risk similarity matrix to learn the hidden spatial context correlations based on graph convolution network. Then we employ the historical traffic speed of road segments to learn the temporal dependency. Lastly, we design a context-aware attention mechanism to adaptively learn the heterogeneous traffic features for incident duration prediction. Extensive experiments on two large-scale real-world datasets from DiDi ride-hailing platform demonstrate the effectiveness of TimeBird.