Short-Term Traffic Data Forecasting: A Deep Learning Approach

Accurate and timely traffic forecasting plays an important role in the development of intelligent transportation systems (ITS). Traffic data are the main information source for various tasks solved as part of the ITS, including traffic management, urban planning, route guidance, and others. Due to the spatial and temporal nonlinearity and complexity of traffic flow, traffic forecasting problem remains a subject of research. In this paper, we design a deep-learning framework that combines convolution operations on graph data with recurrent neural networks to solve the short-term traffic data forecasting problem. The proposed model takes into account recent, daily, and weekly periodic time series to capture different patterns in traffic flow. The experimental study of the model conducted on publicly available real-world datasets shows that the proposed model outperforms other baseline methods.