Traffic Flow Prediction Using Deep Learning: Advances, Challenges, and Future Directions
DOI:
https://doi.org/10.61173/84w6wz64Keywords:
Deep learning, Traffic flow prediction, Spatiotemporal dependencies, Multimodal data fusion, Edge computingAbstract
As urbanization accelerates globally and intelligent transportation technologies rapidly progress, the accurate prediction of road traffic has emerged as a critical issue in the field of smart transportation. This paper introduces a comprehensive review of current research on traffic flow prediction utilizing deep learning and related technologies. It analyzes the limitations of current methods, such as poor generalization to spatiotemporal heterogeneity, reliance on external influencing factors, data quality and quantity issues, and insufficient model explainability and computational scalability. Furthermore, the paper outlines the development trends of the field from the perspective of multimodal data fusion, ultimodal data fusion and federated learning. The study also discusses fuproposing a three-layer fusion framework of data, models, and systems. Emphasis is placed on ensuring data security and privacy through mture directions, including dynamic feature modeling, system deployment at the edge, and real-time prediction. By analyzing the architecture and challenges of current predictive models, this article offers theoretical direction and technological insights for the advancement of intelligent transportation technology.
References
[1] Liebig T, Piatkowski N, Bockermann C, Morik K. Dynamic route planning with real-time traffic predictions. Information Systems, 2017, 64: 258–265.
[2] Shi, Q. X., & Zheng, W. Z. (2004). A comparison of shortterm traffic flow prediction methods for road networks. Journal of Transportation Engineering, (04), 68–71, 83.
[3] Lin, H., Li, L. X., & Wang, H. (2020). A review of research and applications of support vector machines in intelligent transportation systems. Journal of Computer Science and Exploration, 14(06), 901–917.
[4] Ma X, Dai Z, He Z, Ma J, Wang Y, Wang Y. Learning traffic as images: a deep convolutional neural network for large-scale transportation network speed prediction. Sensors, 2017, 17(4): 818.
[5] Yu D, Liu Y, Yu X. A data grouping CNN algorithm for short-term traffic flow forecasting. Proceedings of the 2016 International Conference on Neural Information Processing (ICONIP). Berlin: Springer, 2016: 92–103.
[6] Yang D, Li S, Peng Z, et al. MF-CNN: Traffic flow prediction using convolutional neural network and multi-features fusion. IEICE Transactions on Information and Systems, 2019, E102. D(8): 1526-1536.
[7] Yu F, Wei D, Zhang S, Li J, Chen M. 3D CNN-based accurate prediction for large-scale traffic flow. Proceedings of the 2019 4th International Conference on Intelligent Transportation Engineering (ICITE). Singapore: IEEE, 2019: 99–103.
[8] Guo S, Lin Y, Li S, Chen Z, Wan H. Deep spatial-temporal 3D convolutional neural networks for traffic data forecasting. IEEE Transactions on Intelligent Transportation Systems, 2019, PP(early access): 1–14.
[9] Wu B, Liang X, Zhang S, Xu R. Advances and applications of graph neural networks: A survey. Journal of Computer Research and Development, 2022, 45(01): 35–68.
[10] Kipf TN, Welling M. Semi-supervised classification with graph convolutional networks. Proceedings of the 5th International Conference on Learning Representations (ICLR). Toulon, France: ICLR, 2017: 1–10.
[11] Abu-El-Haija S, Perozzi B, Al-Rfou R, et al. Watch your step: Learning node embeddings via graph attention. Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS). Montréal, Canada: NIPS, 2018: 9198–9208.
[12] Li Y, Yu R, Shahabi C, Liu Y. Graph Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting. 2017-07-06 [2024-12-26].
[13] Wang Q, Lu Q X, Shi P. Multi-graph diffusion attention network for traffic flow prediction. Computer Applications, 2024, (0): 1–10 [2024-12-23]. Dean&Francis ISSN 2959-6157
[14] Praveen Kumar B, Hariharan K. Multivariate Time Series Traffic Forecast with Long Short-Term Memory based Deep Learning Model. IEEE. 2020 International Conference on Power, Instrumentation, Control and Computing (PICC). Thrissur, India: IEEE, 2020: 1–5.
[15] Yang B, Sun S, Li J, Lin X, Tian Y. Traffic flow prediction using LSTM with feature enhancement. Neurocomputing, 2019, 332(C): 320–327.
[16] Yu D X, Qiu S, Zhou H X, Wang Z R. Short-term traffic flow prediction at intersections based on the GRU-RNN model. Highway Engineering, 2020, 45(04): 109–114.
[17] Al-Thani MG, Sheng Z, Cao Y, et al. Traffic Transformer: Transformer-based framework for temporal traffic accident prediction. AIMS Mathematics, 2024, 9(5): 12610-12629.
[18] Liang Y, Cui Z, Tian Y, Chen H, Wang Y.ADeep Generative Adversarial Architecture for Network-Wide Spatial-Temporal Traffic-State Estimation. Transportation Research Record, 2018, 2672(45): 87–105.
[19] Zhang Y, Wang S, Chen B, Cao J, Huang Z. TrafficGAN: Network-Scale Deep Traffic Prediction with Generative Adversarial Nets. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(1): 219–230.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
