Wavelet-HST: A Wavelet-Based Higher-Order Spatio-Temporal Framework for Urban Traffic Speed Prediction

Abstract

As a crucial part of the Intelligent Transportation System, traffic forecasting is of great help for traffic management and guidance. However, predicting short-term traffic conditions on a large-scale road network is challenging due to the complex spatio-temporal dependencies found in traffic data. Previous studies used Euclidean proximity or topological adjacency to explore the spatial correlation of traffic flows, but did not consider the higher-order connectivity patterns exhibited in a road network, which have a significant influence on traffic propagation. Meanwhile, traffic sequences display distinct multiple time-frequency properties, yet few researchers have made full use of this resource. To fill this gap, we propose a novel hybrid framework – Wavelet-based Higher-order Spatial-Temporal method (Wavelet-HST) to accurately predict network-scale traffic speeds. Wavelet-HST first uses discrete wavelet transform (DWT) to decompose raw traffic data into several components with different frequency sub-bands. Then a motif-based graph convolutional recurrent neural network (Motif-GCRNN) is proposed to learn the higher-order spatio-temporal dependencies of traffic speeds from low-frequency components, and auto-regressive moving average (ARMA) models are employed to simulate random fluctuations from the high-frequency components. We evaluate the framework on a traffic dataset collected in Chengdu, China, and experimental results demonstrate that Wavelet-HST outperforms six state-of-art prediction methods by an improvement of 7.8% ~10.5% in the root mean square error.