How Toll Roads Reshape Structural Vulnerability in Primary Road Networks: A Graph Neural Network Learning from Central Java Province

Authors

  • Berlian Kushari Faculty of Engineering, Hasanuddin University, Makassar, INDONESIA and Faculty of Civil Engineering and Planning, Islamic University of Indonesia, Yogyakarta, INDONESIA
  • Muhammad Isran Ramli Faculty of Engineering, Hasanuddin University, Makassar, INDONESIA
  • Bambang Bakri Faculty of Engineering, Hasanuddin University, Makassar, INDONESIA
  • Ardy Arsyad Faculty of Engineering, Hasanuddin University, Makassar, INDONESIA

DOI:

https://doi.org/10.22146/jcef.28441

Keywords:

Primary road network, Vulnerability, Structural connectivity, Graph Neural Network, Toll roads

Abstract

The roles of primary road networks in maintaining regional connectivity, supporting economic activities, and enabling emergency response, especially in disaster-prone areas, are well known. Vulnerability analysis of such networks is commonly conducted following disruption-based scenarios, in which external hazards are modeled to disrupt and degrade network performance. This study adopts a different perspective by considering vulnerability as a property that can also arise from the network’s own topological structure. In this approach, vulnerability is assumed to exist even prior to external disturbances, and thus is an intrinsic characteristic of the network. To explore this idea, a Graph Neural Network (GNN)-based framework is proposed to learn structural vulnerability directly from network topology. The primary road network of Central Java Province, Indonesia, was used as a case study. The network was modeled as an undirected, weighted graph representing two configurations: without toll roads and with toll road integration. Vulnerability labels at the node level were derived from a series of node removal experiments, capturing efficiency loss, connectivity degradation, and network fragmentation. A Graph Convolutional Network (GCN) model with two GCN layers was then trained to learn patterns associated with structural vulnerability based on node features and graph connectivity. The results indicate that structural vulnerability can be learned as a network property, with the model achieving an accuracy of approximately 82% across both configurations. This performance exceeds that of conventional centrality-based approximations. The findings also show that the inclusion of toll roads reshapes the distribution of vulnerability across the network. This supports the interpretation that toll roads act as structural modifiers by reconfiguring systemic vulnerability rather than simply increasing redundancy.

References

Albert, R., Jeong, H. and Barabási, A.-L. (2000), ‘Error and attack tolerance of complex networks’, Nature 406(6794), 378–382. URL: https://doi.org/10.1038/35019019

Alizadeh, D. and Dodge, S. (2025), ‘Disaster vulnerability in road networks: A data-driven approach through analyzing network topology and movement activity’, International Journal of Geographical Information Science 39(5), 1035–1056. URL: https://doi.org/10.1080/13658816.2024.2411001

Bergantino, A., Gardelli, A. and Rotaris, L. (2024), ‘Assessing transport network resilience: Empirical insights from real-world data studies’, Transport Reviews 44(4), 834–857. URL: https://doi.org/10.1080/01441647.2024.2322434

Bishop, C. and Nasrabadi, N. (2006), Pattern Recognition and Machine Learning, Springer. Crucitti, P., Latora, V. and Porta, S. (2006), ‘Centrality measures in spatial networks of urban streets’, Physical Review E 73(3), 036125. URL: https://doi.org/10.1103/PhysRevE.73.036125

Glorot, X. and Bengio, Y. (2010), Understanding the difficulty of training deep feedforward neural networks, in Y. Teh and M. Titterington, eds, ‘Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics’, Proceedings of Machine Learning Research, Chia Laguna Resort, Sardinia, Italy, pp. 249–256. URL: https://proceedings.mlr.press/v9/glorot10a.html

Goodfellow, I., Bengio, Y. and Courville, A. (2016), Deep Learning, MIT Press, Cambridge, MA. Guze, S. (2019), ‘Graph theory approach to the vulnerability of transportation networks’, Algorithms 12(12), 270. URL: https://doi.org/10.3390/a12120270

Hamilton, W., Ying, Z. and Leskovec, J. (2017), Inductive representation learning on large graphs, in I. e. a. Guyon, ed., ‘Advances in Neural Information Processing Systems’, Curran Associates, Inc. URL: https://proceedings.neurips.cc/paper/2017/hash/5dd9db5e033da9c6fb5ba83c7a7ebea9-Abstract.html

Henke, I., Troiani, G. and Pagliara, F. (2024), ‘An analysis of the vulnerability of road networks in response to disruption events through accessibility indicators specification’, Transportation Planning and Technology 47(5), 628–655. URL: https://doi.org/10.1080/03081060.2024.2329650

Jenelius, E. (2009), ‘Network structure and travel patterns: Explaining the geographical disparities of road network vulnerability’, Journal of Transport Geography 17(3), 234–244. URL: https://doi.org/10.1016/j.jtrangeo.2008.06.002

Kingma, D. and Ba, J. (2017), ‘Adam: A method for stochastic optimization’. arXiv:1412.6980. URL: https://arxiv.org/abs/1412.6980

Kipf, T. and Welling, M. (2016), ‘Semi-supervised classification with graph convolutional networks’, arXivpreprint arXiv:1609.02907. URL: https://arxiv.org/abs/1609.02907

Latora, V. and Marchiori, M. (2001), ‘Efficient behavior of small-world networks’, Physical Review Letters 87(19), 198701. URL: https://doi.org/10.1103/PhysRevLett.87.198701

Lin, J. and Lin, W. (2022), ‘Transportation system vulnerability assessment considering environmental impact’, Journal of Advanced Transportation 2022, 1–12. URL: https://doi.org/10.1155/2022/8711894

Lu, Q., Xu, P. and Zhang, J. (2021), ‘Infrastructurebased transportation network vulnerability modeling and analysis’, Physica A: Statistical Mechanics and its Applications 584. URL: https://doi.org/10.1016/j.physa.2021.126350

Mattsson, L.-G. and Jenelius, E. (2015), ‘Vulnerability and resilience of transport systems – a discussion of recent research’, Transportation Research Part A: Policy and Practice 81, 16–34. URL: https://doi.org/10.1016/j.tra.2015.06.002

Newman, M. E. J. (2010), Networks: An Introduction, Oxford University Press, Oxford. Olii, M. R., Nento, S., Doda, N., Olii, R. S. N., Djafar, H. and Pakaya, R. (2025), ‘Transformation of geospatial modelling of soil erosion susceptibility using machine learning’, Journal of the Civil Engineering Forum 11(2), 217–232. URL: https://doi.org/10.22146/jcef.19581

ReddyPriya, M. et al. (2026), ‘Integrating machine learning techniques for critical node identification in complex networks’, Scientific Reports 16(1), 8929. URL: https://doi.org/10.1038/s41598-026-40778-y

Redzuan, A. et al. (2022), ‘Road network vulnerability based on diversion routes to reconnect disrupted road segments’, Sustainability 14(4), 2244. URL: https://doi.org/10.3390/su14042244

Sant’Ana da Silva, E., Pedrini, H. and Santos, A. d. (2023), ‘Applying graph neural networks to support decision making on collective intelligent transportation systems’, IEEE Transactions on Network and Service Management 20(4), 4085–4096. URL: https://doi.org/10.1109/TNSM.2023.3257993

Seyedi, I. et al. (2025), ‘Structural vulnerability assessment in urban transport networks: A network-wide geometric approach using gromov-wasserstein’. URL: https://arxiv.org/abs/2510.24306

Taylor, M. (2017), Vulnerability Analysis for Transportation Networks, Elsevier, Amsterdam.

Wang, J. et al. (2017), ‘Research on the robustness of interdependent networks under localized attack’, Applied Sciences 7(6), 597. URL: https://doi.org/10.3390/app7060597

Wu, Z. et al. (2021), ‘A comprehensive survey on graph neural networks’, IEEE Transactions on Neural Networks and Learning Systems 32(1), 4–24. URL: https://doi.org/10.1109/TNNLS.2020.2978386

Xue, J. et al. (2025), ‘Data science in transportation networks with graph neural networks: A review and outlook’, Data Science for Transportation 7(2), 10. URL: https://doi.org/10.1007/s42421-025-00124-6

Yu, B., Lee, Y. and Sohn, K. (2020), ‘Forecasting road traffic speeds by considering area-wide spatiotemporal dependencies based on a graph convolutional neural network (gcn)’, Transportation Research Part C: Emerging Technologies 114, 189–204. URL: https://doi.org/10.1016/j.trc.2020.02.013

Yu, E.-Y. et al. (2020), ‘Identifying critical nodes in complex networks via graph convolutional networks’, Knowledge-Based Systems 198, 105893. URL: https://doi.org/10.1016/j.knosys.2020.105893

Zeleke, Y., Tira, M. and Scaini, C. (2026), ‘Resilience of road networks to natural hazards: A systematic literature review’, Transportation Engineering 23, 100420. URL: https://doi.org/10.1016/j.treng.2026.100420

Zhang, J., Wang, S. and Wang, X. (2018), ‘Comparison analysis on vulnerability of metro networks based on complex network’, Physica A: Statistical Mechanics and its Applications 496, 72–78. URL: https://doi.org/10.1016/j.physa.2017.12.094

Downloads

Published

2026-07-20

How to Cite

Kushari, B., Ramli, M. I., Bakri, B., & Arsyad, A. (2026). How Toll Roads Reshape Structural Vulnerability in Primary Road Networks: A Graph Neural Network Learning from Central Java Province. Journal of the Civil Engineering Forum, 12(3), 375–388. https://doi.org/10.22146/jcef.28441

Issue

Vol. 12 No. 3 (September 2026)

Section

Articles

License

Copyright is granted to authors for the purpose of providing protection for articles written to describe experiments and their results. JCEF will protect and defend the work and reputation of the author and are also willing to address any allegations of violation, plagiarism, fraud, etc. against articles written and published by JCEF.  JCEF is published under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0). The author holds the copyright and assigns the journal rights to the first publication (online and print) of the work simultaneously.