An Enhanced TimesNet-SARIMA Model for Predicting Outbound Subway Passenger Flow with Decomposition Techniques
Source abstract
Abstract
The accurate prediction of subway passenger flow is crucial for managing urban transportation systems. This research introduces a hybrid forecasting approach that combines an enhanced TimesNet model, Seasonal Autoregressive Integrated Moving Average (SARIMA), and Variational Mode Decomposition (VMD) to improve passenger flow prediction. The method decomposes time series data into Intrinsic Mode Functions (IMFs) using VMD, followed by adaptive predictions for each IMF with TimesNet and SARIMA. The dataset spans from 1 January to 25 January 2019, encompassing 70 million records processed into five-minute intervals. The results show that the VMD preprocessing effectively extracts features, enhancing prediction performance (13.25% MAE, 19.7% RMSE improvements). The hybrid method excels during peak times (52.75% MAE, 50.61% RMSE improvements) and outperforms baseline models like Informer and Crossformer, achieving 66.14% and 63.24% improvements in the MAE and RMSE, respectively. This research offers a reliable tool for predicting subway passenger flow, supporting the smart evolution of urban transport systems.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Traffic Prediction and Management Techniques · Traffic and Road Safety · Transportation Planning and Optimization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Urban Rail Transit and Logistics College, Beijing Union University, Beijing 100101, China
Research Center for Traffic Safety Theory and Application, Beijing Union University, Beijing 100101, China
Department of Engineering Leadership and Society, Drexel University, Philadelphia, PA 19104, USA
Funding
China National Key R&D Program · R&D Program of Beijing Municipal Education Commission
References (38)
Show source-provided references
1. Urban traffic flow prediction techniques: A review
2. Feng, S., and Cai, G. (2016). Passenger flow forecast of metro station based on the ARIMA model. Proceedings of the 2015 International Conference on Electrical and Information Technologies for Rail Transportation, Springer.10.1007/978-3-662-49370-0_49 ↗
3. A novel wavelet-SVM short-time passenger flow prediction in Beijing subway system10.1016/j.neucom.2015.03.085 ↗
4. Predicting bus passenger flow and prioritizing influential factors using multi-source data: Scaled stacking gradient boosting decision trees10.1109/TITS.2020.3035647 ↗
5. Niu, Q., Wang, G., Liu, B., Zhang, R., Lei, J., Wang, H., and Liu, M. (2023). Selection and prediction of metro station sites based on spatial data and random forest: A study of Lanzhou, China. Sci. Rep., 13.10.1038/s41598-023-49877-6 ↗
6. Han, Y., Wang, S., Ren, Y., Wang, C., Gao, P., and Chen, G. (2019). Predicting station-level short-term passenger flow in a citywide metro network using spatiotemporal graph convolutional neural networks. ISPRS Int. J. Geo.-Inf., 8.10.3390/ijgi8060243 ↗
7. Metro passenger flow prediction via dynamic hypergraph convolution networks10.1109/TITS.2021.3072743 ↗
8. An origin–destination passenger flow prediction system based on convolutional neural network and passenger source-based attention mechanism10.1016/j.eswa.2023.121989 ↗
9. Study on Subway passenger flow prediction based on deep recurrent neural network10.1007/s11042-020-09088-x ↗
10. Metro passenger flow prediction model using attention-based neural network10.1109/ACCESS.2020.2973406 ↗
11. A hybrid model for metro passengers flow prediction10.1080/21642583.2023.2191632 ↗
12. Hybrid models of subway passenger flow prediction based on convolutional neural network10.1049/itr2.12298 ↗
13. The empirical mode decomposition and the Hilbert spectrum for non-linear and non-stationary time series analysis. Proceedings of the Royal Society of London10.1098/rspa.1998.0193 ↗
14. A Time Series Decomposition and Reinforcement Learning Ensemble Method for Short-Term Passenger Flow Prediction in Urban Rail Transit10.1007/s40864-023-00205-1 ↗
15. Rhif, M., Ben Abbes, A., Farah, I.R., Martínez, B., and Sang, Y. (2019). Wavelet Transform Application for/in Non-Stationary Time-Series Analysis: A Review. Appl. Sci., 9.10.3390/app9071345 ↗
16. Improved complete ensemble empirical mode decomposition with adaptive noise and composite multiscale permutation entropy for denoising blast vibration signal10.1016/j.heliyon.2024.e37339 ↗
17. Non-linear Time Series Prediction using Improved CEEMDAN, SVD and LSTM10.1007/s11063-024-11622-z ↗
18. Zhu, J., Xu, W.X., Jin, H.T., and Sun, H. (2016, January 1–4). Prediction of urban rail traffic flow based on multiply Wavelet-ARIMA model. Proceedings of the 7th International Conference on Green Intelligent Transportation System and Safety, Nanjing, China.
19. LightGBM-based model for metro passenger volume forecasting10.1049/iet-its.2020.0396 ↗
20. Metro passenger flow forecasting through multi-source time-series fusion: An ensemble deep learning approach10.1016/j.asoc.2022.108644 ↗
21. A hybrid approach based on variational mode decomposition for analyzing and predicting urban travel speed10.1155/2019/3958127 ↗
22. A new traffic flow prediction model based on cosine similarity variational mode decomposition, extreme learning machine and iterative error compensation strategy10.1016/j.engappai.2022.105234 ↗
23. Combination time frequency and empirical wavelet transform methods for removal of composite noise in EMG signals
24. Sequence to sequence learning with attention mechanism for short-term passenger flow prediction in large-scale metro system10.1016/j.trc.2019.08.005 ↗
25. SARIMA modelling approach for railway passenger flow forecasting
26. Wu, H., Hu, T., and Liu, Y. (2022). Timesnet: Temporal 2D-variation modeling for general time series analysis. arXiv.
27. Zuo, C., Wang, J., Liu, M., Deng, S., and Wang, Q. (2023). An Ensemble Framework for Short-Term Load Forecasting Based on TimesNet and TCN. Energies, 16.10.3390/en16145330 ↗
28. Weekly solar irradiation forecasting method based on ICCEMDAN and TimesNet networks10.1016/j.renene.2023.119706 ↗
29. Short-Term Subway Inbound Passenger Flow Prediction Based on AFC Data and PSO-LSTM Optimized Model10.1007/s40864-022-00166-x ↗
30. A multi-agent reinforcement learning framework for optimizing financial trading strategies based on TimesNet10.1016/j.eswa.2023.121502 ↗
31. Graph transformer embedded deep learning for short-term passenger flow prediction in urban rail transit systems: A multi-gate mixture-of-experts model10.1016/j.ins.2024.121095 ↗
32. A practical method for calculating largest Lyapunov exponents from small data sets10.1016/0167-2789(93)90009-P ↗
33. Profit prediction using ARIMA, SARIMA and LSTM models in time series forecasting: A Comparison10.1109/ACCESS.2022.3224938 ↗
34. Forecasting the monthly incidence of scarlet fever in Chongqing, China using the SARIMA model10.1017/S0950268822000693 ↗
35. Soft computing techniques for rainfall-runoff simulation: Local non-parametric paradigm vs. model classification methods10.1007/s11269-017-1711-9 ↗
36. Variational mode decomposition10.1109/TSP.2013.2288675 ↗
37. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR.2015.7298594 ↗
38. Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., and Liu, Z. (2020, January 13–19). Dynamic convolution: Attention over convolution kernels. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01104 ↗