Short-Term Passenger Flow Prediction of Suzhou Metro Using Random Forest and LSTM

DOI

10.2991/978-94-6239-648-7_15How to use a DOI?

Keywords

Suzhou; Metro; Random Forest; LSTM

Abstract

In the operation of urban public transportation, the volatility of subway passenger flow stands as a key issue affecting operational efficiency and passenger experience. Congestion during peak passenger flow periods, wasted transport capacity during off-peak hours, and sudden changes in passenger flow under special scenarios such as holidays not only increase the difficulty of operational dispatching, but also easily lead to extended passenger waiting times and reduced travel comfort. To address the fluctuation of metro passenger flow and enhance operational efficiency and passenger experience, this paper develops a short-term prediction model for Suzhou Metro passenger flow in 2025 by integrating Random Forest with Long Short-Term Memory (LSTM). Random Forest is employed to select key features, including historical passenger volume, holidays, weather conditions, line attributes, and social events, which significantly influence flow variations. The LSTM component then effectively captures complex temporal dependencies and nonlinear patterns in the data, improving prediction accuracy. Experimental results demonstrate that the proposed hybrid model exhibits strong generalization capability and reliable prediction performance under various conditions, such as peak hours, holidays, and emergencies. This approach provides effective data-driven support for dynamic metro scheduling, resource allocation, and operational management, contributing to reduced congestion and improved service quality for passengers.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Kai Zhang
AU  - Lixun Zhuang
PY  - 2026
DA  - 2026/04/24
TI  - Short-Term Passenger Flow Prediction of Suzhou Metro Using Random Forest and LSTM
BT  - Proceedings of the International Workshop on Advances in Deep Learning for Image Analysis and Computer Vision (IWADIC 2025)
PB  - Atlantis Press
SP  - 128
EP  - 135
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6239-648-7_15
DO  - 10.2991/978-94-6239-648-7_15
ID  - Zhang2026
ER  -