Traffic flow prediction is an important problem in the field of intelligent transportation systems. Most existing traffic-flow prediction methods have made good progress, which however still face the following two key challenges. (1) The underlying pattern of traffic flow depends on not only the historical information along the timeline, but also the information of spatially adjacent areas, making it a challenging problem on how to balance the two temporal-spatial patterns; (2) Due to fact that time information has the characteristic of multiple granularity, such as hour, day and week, how to capture the multi-grained temporal patterns is another challenge problem. In this paper, we design a multi-grained spatio-temporal deep regression model (MGSTDR) to address the above challenges. By extending the typical autoregressive integrated moving average model (ARIMA) on the basis of multi-grained spatio-temporal traffic flow information, the proposed model can effectively use historical information along the timeline as well as the information of adjacent regions, such that the prediction of multi-grained spatio-temporal traffic flow can be performed. Experimental results on several datasets demonstrate that the proposed model outperforms existing benchmark methods on the task of multi-granularity, and particularly obtains an approximately 5.66% improvement in the hourly traffic flow prediction.

Traffic flow prediction is an important issue of the intelligent traffic control and management systems. However, traffic flow data has nonlinear and complex characteristics in both time and space, making it challenging to accurately predict it. In this regard, this paper proposes a Graph temopral recurrent independent mechanisms (G-tRIM) model, which uses Graph attention networks (GAT) to effectively capture the spatial dependencies of traffic flow data, and uses Recurrent independent mechanisms (RIM) to accurately characterize the latent state of traffic flow data. We conduct experiments on the Beijing and Guizhou datasets, and the experimental results show that our proposed G-tRIM outperforms the baseline models on both datasets in terms of MSE and MAE.