Improved Dynamic Coupled Graph Convolutional Recurrent Networks for Traffic Forecasting

Traffic forecasting is a crucial application of the Intelligent Transportation System (ITS), with research focusing on various methods, from classical statistical approaches to graph-based methods integrated with RNN-based approaches to capture spatial and temporal correlations simultaneously. During the traffic data collection phase, the absence of vehicles on each road or sensor malfunctions can result in the collection of traffic time series data as zeros. However, storing such zero values makes accurate traffic prediction more challenging. To address this challenge, we present a novel model for improving traffic forecasting using graph convolutional recurrent neural networks. The proposed method is evaluated on two real-world public benchmark datasets and compared with six baseline models, showcasing its superior performance.