Multi-scale attention graph convolutional recurrent network for traffic forecasting

In the backdrop of an ever-expanding urban transportation road network, the dramatic changes in traffic flow make traffic flow forecasting become a challenge. Which encompass intricate spatial correlations and intricate non-linear temporal relationships. Given a complex time series of traffic flow, accurately predicting traffic flow under such circumstances becomes an arduous task, particularly for long-term sequences. To tackle this conundrum, we put together a traffic prediction framework called the multi-scale attention-based graph convolutional recurrent network (MAGRN). Based on GCN and RNN, this framework skilfully extracts dynamic spatial and temporal features from node attributes. By incorporating multi-scale feature extraction and two attention mechanisms within the attention structure, MAGRN adeptly captures features at varying granularities. This enables MAGRN to diligently capture both the temporal interdependencies and spatial correlations inherent in traffic sequences, thereby minimizing errors. Experimental validation on three real-world traffic datasets unequivocally attests to the superior performance of the MAGRN model.