Abstract

Accurate traffic flow forecasting is the foundation of intelligent transportation systems. This study proposes a spatio-temporal graph neural network that jointly models the graph structure of the road network and temporal dependencies. The model was evaluated on six months of data from 207 sensors in Istanbul and on PeMS-BAY. The proposed method reduced the mean absolute error of 30-minute forecasts by 9.4% compared with DCRNN. The contribution of representing weekend and holiday patterns with separate embeddings was analysed.

Keywords:traffic forecastinggraph neural networkssmart citytime seriesdeep learning

Full Text

PDF Download · 8 KB

Declarations

Ethics Approval
This study does not require ethics committee approval.
Conflict of Interest
The authors declare no conflict of interest.

References 5

  1. Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In International Conference on Learning Representations.
  2. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
  3. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
  4. Gubbi, J., Buyya, R., Marusic, S., & Palaniswami, M. (2013). Internet of Things (IoT): A vision, architectural elements, and future directions. Future Generation Computer Systems, 29(7), 1645–1660. https://doi.org/10.1016/j.future.2013.01.010
  5. Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In International Conference on Learning Representations.

How to Cite

Yavaş, E., & Hasanović, T. (2025). Spatio-Temporal Graph Neural Networks for Traffic Flow Forecasting in Smart Cities. International Journal of Science and Technology Research, 7(1), 33–45. https://doi.org/10.99999/ubtad.2025.9
BibTeX RIS (EndNote, Zotero, Mendeley)

License

CC BY 4.0

© 2025 Emre Yavaş, Tarık Hasanović. This article is distributed under the terms of the CC BY 4.0 license, which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. License text