Learning Traffic as Images: A Deep Convolution Neural Network for Large-scale Transportation Network Speed Prediction

This paper proposes a convolution neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with high accuracy. Spatiotemporal traffic dynamics is converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest. The results show that the proposed method outperforms the four algorithms by an average accuracy improvement of 27.96% within acceptable execution time. The CNN can train the model in reasonable time and thus are suitable for large-scale transportation networks.