MetroEye: A Weather-Aware System for Real-Time Metro Passenger Flow Prediction

Abstract

Real-time passenger flow prediction plays an important role in subway network design and management. Most of the existing prediction algorithms only consider the sequence of passenger flow volume, however, ignore the influence of other outer factors, for example, the weather conditions, air quality and temperature. In this paper, a systematic framework, MetroEye, is proposed for weather-aware prediction of real-time passenger flow. The framework contains an offline system and an online system. The offline system adopts a conditional random field (CRF) model to establish the relationship between passenger flow volume and weather factors. Experimental results show the superior prediction accuracy of the model, especially in large stations. The online system provides efficient methods to simulate the real-time passenger flow volume. Due to its high practicality, MetroEye has been adopted by Beijing Urban Rail Transit Control Center to monitor the passenger flow status of the Beijing subway system.

Metro Passenger Flow Forecasting Using 2A-LSTM with Multi-source Data

“…Tang [7] and Wang [8] have studied the influence of external weather factors on passenger flow forecasting successively. They analysed the correlation between weather factors (such as weather conditions, air quality and temperature) and passenger travel.…”