Short-term Subway Passenger Flow Prediction based on LSTM and ARIMA Model

Yunhao Ma

doi:10.54097/atd3z228

Authors

Yunhao Ma

DOI:

https://doi.org/10.54097/atd3z228

Keywords:

LSTM; ARIMA; passenger flow prediction.

Abstract

With the acceleration of urbanization, urban traffic problems have become increasingly severe. To alleviate urban traffic congestion, the development of public transportation has been greatly emphasized. As a convenient and rapid means of urban travel, the metro has become the preferred choice for citizens, leading to significant passenger flow pressure. Therefore, it is crucial to forecast passenger flow in advance. This paper utilizes passenger flow data from Chengdu Metro Line 1 from May to September 2019 to conduct a study. LSTM and ARIMA models were constructed to simulate the actual passenger flow data. The prediction performance of both models shows that the trends simulated by these models fit the original data well, verifying their applicability in passenger flow forecasting. Furthermore, it was found that the LSTM model outperformed the ARIMA model among the constructed models in this paper. Accurate metro passenger flow forecasting can help relevant departments manage the metro system more effectively, thereby improving passenger travel efficiency and safety.

Downloads

Download data is not yet available.

References

[1] Pan N. Urban rail transit passenger flow prediction based on ARIMA and LSTM. Scientific and Technological Innovation, 2022, (08): 165-168.

[2] He A, Wang B. Urban rail transit OD passenger flow prediction method based on improved LSTM algorithm. Comprehensive Transportation, 2021, 43(04): 67-72+87.

[3] Du X, Zhao X, Li L. Short-term passenger flow prediction of rail transit based on LSTM. Journal of Guizhou University, 2021, 38(05): 109-118.

[4] Xue Q, Zhang W, Ding M, et al. Passenger flow forecasting approaches for urban rail transit: A survey. International Journal of General Systems, 2023, 52(8): 919-947. DOI: https://doi.org/10.1080/03081079.2023.2231133

[5] Ren N. Short-term passenger flow prediction of urban rail transit using deep learning algorithms. System Simulation Technology, 2021, 17(04): 259-264.

[6] Cui H, Chen X, Yang, C, et al. Subway station passenger flow prediction based on deep long short-term memory network. Urban Rail Transit Research, 2019, 22(09): 41-45.

[7] Liu Y, Liu Z, Jia R. DeepPF: A deep learning based architecture for metro passenger flow prediction. Transportation Research Part C: Emerging Technologies, 2019, 101(APR): 18-34. DOI: https://doi.org/10.1016/j.trc.2019.01.027

[8] Zhao Q, Feng X, Zhang L, et al. Research on short-term passenger flow prediction of LSTM rail transit based on wavelet denoising. Mathematics, 2023, 11(19): 4204. DOI: https://doi.org/10.3390/math11194204

[9] Qi X, Fu C. Improved LSTM method for short-term subway passenger flow prediction. Transportation Technology and Economy, 2024, 26(02): 58-64.

[10] Liu X. Passenger flow data prediction of rail transit stations based on deep learning. Beijing University of Posts and Telecommunications, 2024.

[11] Zhang Y. Short-term passenger flow prediction method for urban rail transit based on deep learning. Lanzhou Jiaotong University, 2022. DOI: https://doi.org/10.20944/preprints202308.1206.v1

[12] Liu X. Passenger flow data prediction of rail transit stations based on deep learning. Beijing University of Posts and Telecommunications, 2024.