A comparative evaluation of established and contemporary deep learning traffic prediction methods

Traffic prediction is an essential component in intelligent transportation systems. Various methods have been developed to solve this challenging problem over the years, including time series models, regression models, and, more recently, deep learning models. This chapter provides an unbiased comparison of these methods under a variety of settings and also addresses the critical question of whether deep learning approaches can offer significant improvements over classical machine learning methods. A traffic simulation model of the Greater Toronto Area was used to generate traffic data for a stretch of highway as well as an urban region. Using these datasets, the methods were compared under five scenarios with different prediction horizons, the presence of missing data, and the presence of traffic events unseen in the training data. Experimental results showed that deep learning methods of traffic prediction, including graph convolutional neural networks, are effective for traffic prediction. Graph neural networks with shared parameters were compact, resistant to overfitting, and performed well in all of the experiments. However, ensemble methods such as random forest regression can generate more accurate predictions at the cost of higher resource consumption during training, which may become a challenge in large transportation networks. Overall, deep learning architectures should be carefully designed by restricting the input to features with known influences on the predictions, which can guide parameter learning and improve performance.