A Temporal Fusion Transformer Approach for Road Traffic Congestion Prediction
Keywords:
Traffic Congestion Prediction, Temporal Fusion Transformer, Deep Learning, ime-Series Forecasting, Intelligent Transportation SystemsAbstract
Traffic congestion is a growing urban challenge, causing economic losses, environmental damage, and increased travel time. Traditional forecasting models struggle to capture complex congestion patterns, necessitating advanced deep learning solutions. This study proposes a Temporal Fusion Transformer (TFT)-based model for predicting road traffic congestion using historical and real-time
data. The dataset, sourced from Kaggle, includes variables such as traffic flow, vehicle speed, weather conditions, time of day, and road occupancy. Data preprocessing involves handling missing values, feature selection, and normalization. The TFT model, known for its ability to process long- sequence dependencies and multi-source data, is trained and optimized using hyperparameter tuning. The model achieves a fixed accuracy of 96.45%, outperforming LSTMs and GRUs in short- term congestion prediction. Evaluation metrics such as MAE, RMSE, and R² confirm its reliability, while visualization techniques validate its predictive power. This study demonstrates TFT’s effectiveness in forecasting traffic congestion, making it a valuable tool for intelligent transportation systems. Future research can explore integrating real-time GPS and IoT sensor data to enhance prediction accuracy further.
References
Zhang, Y., Li, X., Wang, Y., & Liu, Y. (2023). Temporal Fusion Transformer Model for Traffic Flow Prediction. EAI Endorsed Transactions on Scalable Information Systems, 10(1), e3.
Wang, J., Zhang, H., & Li, Y. (2023). Deep Spatial-Temporal Graph Network for Traffic Congestion Prediction. Information, 14(2), 108.
Liu, Z., Chen, Y., & Gao, S. (2023). Fusion Embedding Layer for Traffic Prediction. Applied Sciences, 14(10), 4325.
Smith, J. A., & Brown, L. M. (2024). Deep Learning vs. Traditional Models in Traffic Forecasting: A Comprehensive Review. Journal of Advanced Transportation, 2024, 9981657.
Kumar, R., & Gupta, S. (2022). Traffic Congestion Prediction Using Weather and Time Features: A Machine Learning Approach. International Journal of Transportation Science and Technology, 11(3), 361-374.
Chen, X., Xu, J., & Zhao, B. (2024). MFSTN Model with Transformer and Graph Attention Network for Traffic Flow Prediction. Scientific Reports, 14, 65040.
Lee, S., & Kim, H. (2023). Deep Learning- Based Traffic Flow Prediction Across Multiple Monitoring Stations. Transportation Research Record, 2677(1), 45-57.
Wang, P., & Zhang, D. (2022). Spatio- Temporal Transformer Model for Traffic Congestion Prediction. Journal of Big Data Analytics in Transportation, 4(2), 77-89.
Huang, C., & Wang, Y. (2019). Deep Autoencoder Neural Network for Short-Term Traffic Prediction. IEEE Access, 7, 110041- 110051.
Li, Y., & Zhang, H. (2017). CNN-Based Traffic Congestion Prediction Using State Matrices. In Computing in Civil Engineering 2017 (pp. 229-236).
Zhao, W., Zhang, S., Zhou, B., & Wang, B. (2024). Criss-Crossed Dual-Stream Transformer for Traffic Forecasting. arXiv preprint arXiv:2403.17753.
Ung, H. Q., Niu, H., Dao, M. S., Wada, S., & Minamikawa, A. (2024). Temporal Attentive Cross-Modality Fusion Transformer (xMTrans) for Long-Term Traffic Prediction. arXiv preprint arXiv:2405.04841. 2388 (2021). https://doi.org/10.3390/agronomy11122388
