Traffic flow prediction based on T-GCN in extreme weather: A case study of Beijing

Abstract

In recent years, frequent extreme weather events have significantly impacted traffic management and urban planning. Consequently, accurate and real-time traffic prediction has become crucial for effective urban traffic planning, management, and control. This study aims to predict road traffic flow in Beijing under extreme weather conditions. To achieve this goal, the study analyses historical weather data of Beijing and identifies four typical extreme weather conditions. Using traffic data collected between 2014 and 2016, the study then employs the time series graph convolutional network (T-GCN) model to predict traffic flow under extreme weather conditions.