Predicting Short-Term Traffic Speed Using a Deep Neural Network to Accommodate Citywide Spatio-Temporal Correlations

The traffic speed on a given road segment is affected by the current and past speeds on nearby segments, and the influence further cascades into the rest of a transport network. Thus, a successful forecasting model should consider not only the impact of neighboring road segments but also that of distant segments. Based on this principle, the approach proposed here projects the topology of a real traffic network into the structure of a deep neural network in order to accommodate citywide spatial correlations as well as temporal dependencies. This approach leads to interesting model interpretations in terms of traffic state transition and propagation, which form a basis for extending the proposed forecasting model. The present study was conducted with a large-scale data set collected over 10 months, and traffic speeds were successfully forecasted for 170 road segments in Gangnam, Seoul, Korea.

Automated summary

This study successfully forecasted traffic speeds for 170 road segments in Gangnam, Seoul, Korea by projecting the topology of a real traffic network into the structure of a deep neural network. The approach considered the impact of neighboring and distant road segments, leading to interesting model interpretations involving traffic state transition and propagation.