Open Access Open Access  Restricted Access Subscription Access

Implementation of Artificial Intelligence System (AI) for Pavement Maintenance Decision Management

Saad Issa Sarsam

Abstract


Serviceability and performance of asphalt concrete pavement (ACP) throughout its design life is usually monitored to detect the possibility of distress in the long-term evaluation of (ACP) surface condition. The right decision to start the maintenance at the right time and the right maintenance alternative is considered and implemented based on such monitoring process. This work demonstrates the implementation of artificial intelligence (AI) systems to assess in the management of (ACP) maintenance decisions. Visual inspection of the road surface using the walk-through techniques for evaluating the (ACP) surface condition was utilized. Common types of (ACP) distresses including potholes, bleeding of asphalt, various cracking types, patching, and horizontal and vertical deformations, with their various intensity and severity level are considered in the data base of the AI system. Distress data are fed to the system. The types of various distresses, severity and intensity are subjected to analysis by the system, and the present pavement condition rating (PCR) is determined as the functional indicator. The decision tree of the AI system suggests the required maintenance action based on the required serviceability classification of the roadway, the expected extension in the service life of the pavement when such maintenance decision is implemented, and the available budget.

 


Full Text:

PDF

References


- Jweihan Y. S. Trustworthy Explainable AI for Asphalt Pavement Engineering: A Systematic Scoping Review of Materials, Performance, and Decision Support. MDPI Appl. Syst. Innov. 2026, 9(7), 133; https://doi.org/10.3390/asi9070133.

- Yang Z. MPA-YOLO: An Automated Detection Algorithm for Asphalt Pavement Distresses on National and Provincial Roads. ADIST '26: Proceedings of the 2026 3rd International Conference on Autonomous Driving and Intelligent Sensing Technology. 13 May 2026. P. 101 – 109. https://doi.org/10.1145/3807211.3807226.

- Dixit S., Chandak P., and Goel, A. Artificial Intelligence Techniques for Pavement Condition Prediction Using Functional and Structural Indicators: A Systematic Review. Springer Nature, Int. J. Pavement Res. Technol. 2026. https://doi.org/10.1007/s42947-026-00744-3.

- Ramadan S., Kassem H., ElKordi A., R. Joumblat R. Incorporating Artificial Intelligence Applications in Flexible Pavements: A Comprehensive Overview. Springer Nature, Int. J. Pavement Res. Technol. 19, P. 902–927 2026. https://doi.org/10.1007/s42947-024-00496-y.

- Asadi Y. Paving the Future of Intelligent Pavement Defect Detection with Machine Learning: A Comprehensive Survey of Techniques and Applications. Springer Nature. Int. J. Pavement Res. Technol. 2026. https://doi.org/10.1007/s42947-026-00711-y.

- Gupta B., Agrawal M., Narooka P., Panwar D., Anand S. Intelligent pavement management: a machine learning framework for condition classification and maintenance prioritization. Sci Rep 16, 19475, 27 April 2026. https://doi.org/10.1038/s41598-026-49953-7.

- He C., Duan Y., Mamat T., Zhu X., Dridi M., Mualla Y., and Abbas-Turki A. Research on a Prediction Method for Maintenance Decision of Expressway Asphalt Pavement Based on Random Forest. MDPI Applied Sciences, Volume 16 Issue 7. https://doi.10.3390/app16073343.

- Tofighi A., Golroo A., Fahmani M. Asphalt pavement deformation distress evaluation using deep learning. Taylor and Francis, International Journal of Pavement Engineering, 26(1). 2025. https://doi.org/10.1080/10298436.2025.2524738.

- Zhang H., Dong Y., Hou Y., Cheng X., Xie P., Di K. Research on Asphalt Pavement Surface Distress Detection Technology Coupling Deep Learning and Object Detection Algorithms. MDPI, Infrastructures 2025, 10(4), 72; https://doi.org/10.3390/infrastructures10040072.

- Ding T., and Wang H. Decision Tree Implementation for Pavement Maintenance and Repair Based on Neural Network Model. ECPDC '24: Proceedings of the 2024 International Academic Conference on Edge Computing, Parallel and Distributed Computing. 2024. P. 170 – 174, https://doi.org/10.1145/3677404.3677433.


Refbacks

  • There are currently no refbacks.