Layerwise Recurrent Autoencoder for General Real-world Traffic Flow Forecasting

Peize Zhao, Danfeng Cai, Shaokun Zhang, Feng Chen, Zhemin Zhang, Cheng Wang, Jonathan Li

Abstract: Accurate spatio-temporal traffic forecasting is a fundamental task that has wide applications in city management, transportation area and financial domain. There are many factors that make this significant task also challenging, like: (1) maze-like road network makes the spatial dependency complex; (2) the traffic-time relationships bring non-linear temporal complication; (3) with the larger road network, the difficulty of flow forecasting grows. The prevalent and state-of-the-art methods have mainly been discussed on datasets covering relatively small districts and short time span, e.g., the dataset that is collected within a city during months. To forecast the traffic flow across a wide area and overcome the mentioned challenges, we design and propose a promising forecasting model called Layerwise Recurrent Autoencoder (LRA), in which a three-layer stacked autoencoder (SAE) architecture is used to obtain temporal traffic correlations and a recurrent neural networks (RNNs) model for prediction. The convolutional neural networks (CNNs) model is also employed to extract spatial traffic information within the transport topology for more accurate prediction. To the best of our knowledge, there is no general and effective method for traffic flow prediction in large area which covers a group of cities. The experiment is completed on such large scale real-world traffic datasets to show superiority. And a smaller dataset is exploited to prove universality of the proposed model. And evaluations show that our model outperforms the state-of-the-art baselines by 6% - 15%.

Keywords: traffic flow forecasting, spatiotemporal dependencies, deep learning, intelligent transportation system

TL;DR: We propose Layerwise Recurrent Autoencoder with effective spatiotemporal dependencies modeling for general traffic flow forecasting.