Comparison SARIMA-LSTM and CNN-LSTM Machine Learning Algorithms in Predicting Time Series Analysis: Road Traffic Accidents Data
Abstract
Traditional time series models may not adequately capture the underlying patterns for prediction in particular time series data. Hybrid machine learning approaches offer a more effective solution. This study compares two hybrid machine learning approaches, Seasonal Autoregressive Integrated Moving Average (SARIMA)-Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN)-LSTM—for time series forecasting of historical road traffic accident counts. The SARIMA-LSTM model combines the ability of SARIMA to capture trend and seasonality with the nonlinear learning capacity of LSTM networks, while the CNN and LSTM model integrates convolutional feature extraction with temporal sequence learning. Time series road traffic accident counts spanning five consecutive years (1399–1403 Iranian calendar) were used to evaluate both models. The findings demonstrate that the CNN-LSTM model consistently outperforms the SARIMA-LSTM approach across all evaluation metrics, achieving significantly lower error rates and providing more reliable forecasts for traffic accident prediction.
Keywords:
Time series models, Hybrid machine learning, SARIMA-LSTM, CNN-LSTMReferences
- [1] Wang, S., Yan, C., & Yong, S. (2023). A review of road traffic accident prediction methods. American journal of management science and engineering, 8(3), 73–77. https://doi.org/10.11648/j.ajmse.20230803.12
- [2] Marcillo, P., Valdivieso Caraguay, Á. L., & Hernández-Álvarez, M. (2022). A systematic literature review of learning-based traffic accident prediction models based on heterogeneous sources. Applied sciences, 12(9), 4529. https://doi.org/10.3390/app12094529
- [3] Sajadi, P., Qorbani, M., Moosavi, S., & Hassannayebi, E. (2025). Accident impact prediction based on a deep convolutional and recurrent neural network model. Urban Science, 9(8), 299. https://doi.org/10.3390/urbansci9080299
- [4] Behboudi, N., Moosavi, S., & Ramnath, R. (2024). Recent advances in traffic accident analysis and prediction: A comprehensive review of machine learning techniques. https://doi.org/10.48550/arXiv.2406.13968
- [5] Yeole, M., Jain, R. K., & Menon, R. (2023). Road traffic accident prediction for mixed traffic flow using artificial neural network. Materials Today: Proceedings, 72, 832–837. https://doi.org/10.1016/j.matpr.2022.11.490
- [6] Babanezhad, M., Khorsha, H., Mohajervatan, A., & Choori, A. (2025). Estimating the demand for ambulances in traffic accidents. Health in emergencies and disasters quarterly, 10(4), 247–258. https://doi.org/10.32598/hdq.10.4.149.8
- [7] Moslehi, S., Gholami, A., Haghdoust, Z., Abed, H., Mohammadpour, S., & Moslehi, M. A. (2021). Prediction of traffic accidents based on weather conditions in Gilan province using artificial neural network. Journal of health administration, 24(2), 67–78. https://doi.org/10.52547/JHA.24.3.67
- [8] Agyemang, E. F., Mensah, J. A., Ocran, E., Opoku, E., & Nortey, E. N. N. (2024). Time series based road traffic accidents forecasting via SARIMA and facebook prophet model with potential changepoints. Heliyon, 10(4), e26051. https://doi.org/10.1016/j.heliyon.2024.e26051
- [9] Lim, B., & Zohren, S. (2021). Time-series forecasting with deep learning: A survey. Philosophical transactions of the royal society A, 379(2194), 20200209. https://doi.org/10.1098/rsta.2020.0209
- [10] Panicker, N. K. K. (2024). Hybrid SARIMA-LSTM approach for improved time series prediction of aerosol optical depth across Delhi, India. Journal of theoretical and applied information technology, 102(11), 4836–4853. https://www.jatit.org/volumes/Vol102No11/14Vol102No11
- [11] Sherstinsky, A. (2020). Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear phenomena, 404, 132306. https://doi.org/10.1016/j.physd.2019.132306
- [12] He, L., Zhang, Z., Liu, Y., & Wang, X. (2021). Using SARIMA–CNN–LSTM approach to forecast daily tourism demand. International journal of hospitality management, 94, 102862. https://doi.org/10.1016/j.ijhm.2021.102862
- [13] Li, G., & Yang, N. (2023). A hybrid SARIMA-LSTM model for air temperature forecasting. Advanced Theory and Simulations, 6(1), 2200502. https://doi.org/10.1002/adts.202200502
- [14] Suryanarayana, S. V., Chand, T. S., Mahesh, D. B., Gurrala, R. R., & Appana, K. K. (2025). Hybrid CNN-LSTM model for accurate time series forecasting: A deep learning approach. In 2025 international conference on sustainable communication networks and application (ICSCN) (pp. 1034–1039). Theni, India: IEEE. https://doi.org/10.1109/ICSCN67106.2025.11308601
- [15] Feng, T., Zheng, Z., Xu, J., Liu, M., Li, M., Jia, H., & Yu, X. (2024). The comparative analysis of SARIMA, Facebook Prophet, and LSTM for road traffic injury prediction in Northeast China. Frontiers in public health, 12, 1418350. https://doi.org/10.3389/fpubh.2024.1418350
Issue 1