Smart Urban Road Management: Application of Artificial Neural Networks for Predictive Modeling of the International Roughness Index
DOI:
https://doi.org/10.26877/asset.v8i4.3703Keywords:
IRI, SDI, ANN, Predictive Modeling, Road MaintenanceAbstract
Road condition assessment is an important indicator within the infrastructure maintenance management system. The International Roughness Index (IRI) is a standard service instrument used in various countries to evaluate road surface roughness. However, assessing road conditions using IRI faces several challenges, including the need for expensive equipment, long operational time and cost, limited coverage, and the fact that it only represents surface roughness, thereby requiring additional surveys to identify pavement distress types directly. The objective of this study is to develop an IRI prediction model based on the Surface Distress Index (SDI) parameters to optimize the efficiency of road condition assessment by using Artificial Neural Networks (ANN) to enhance road maintenance planning. This model was trained on five years of road-damage data across 42 urban road segments. The coefficient of determination from the study findings indicates excellent prediction accuracy, with an R2 value of 0.93, a Mean Absolute Error (MAE) of 0.73, and a Root Mean Square Error (RMSE) of 1.07. This model can serve as a more dynamic strategy for urban road maintenance management in developing countries facing resource limitations. The proposed framework offers an innovative and adaptive solution to issues in road maintenance management and provides support for more sustainable urban infrastructure management.
References
[1] Sandamal K, Madushani JPSS, Muttil N, Rathnayake U. Pavement Roughness Prediction Using Explainable and Supervised Machine Learning Technique for Long-Term Performance. Sustainability 2023;15:9617. https://doi.org/10.3390/su15129617.
[2] Gharieb M, Nishikawa T. Development of Roughness Prediction Models for Laos National Road Network. Civileng 2021;2:158–73. https://doi.org/10.3390/civileng2010009.
[3] Wang G, Burrow M, Ghataora G. Study of the Factors Affecting Road Roughness Measurement Using Smartphones. Journal of Infrastructure Systems 2020;26. https://doi.org/10.1061/(asce)is.1943-555x.0000558.
[4] Al-Samahi S, Zeiada W, Al-Khateeb GG, Hamad K, Alnaqbi A. A Comparative Study of Pavement Roughness Prediction Models Under Different Climatic Conditions. Infrastructures (Basel) 2024;9:167. https://doi.org/10.3390/infrastructures9100167.
[5] Makhmudov F, Turimov D, Xamidov M, Nazarov F, Cho YI. Real-Time Fatigue Detection Algorithms Using Machine Learning for Yawning and Eye State. Sensors 2024;24. https://doi.org/10.3390/s24237810.
[6] Moreno MAR, Marín-Uribe CR, Restrepo-Tamayo LM. Probabilistic Model for Prediction of International Roughness Index Based on Monte Carlo. Ric 2022;37. https://doi.org/10.7764/ric.00021.21.
[7] Tamagusko T, Ferreira A. Machine Learning for Prediction of the International Roughness Index on Flexible Pavements: A Review, Challenges, and Future Directions. Infrastructures (Basel) 2023;8:170. https://doi.org/10.3390/infrastructures8120170.
[8] Allen E, Costello SB, Henning TFP. Quantifying road criticality through the impact of disruptions on pavement deterioration and agency maintenance costs. International Journal of Disaster Risk Reduction 2025;126:105592. https://doi.org/https://doi.org/10.1016/j.ijdrr.2025.105592.
[9] Al-Mansour A, Lee KWW, Al-Qaili AH. Prediction of Pavement Maintenance Performance Using an Expert System. Applied Sciences (Switzerland) 2022;12. https://doi.org/10.3390/app12104802.
[10] Issa A, Samaneh H, Ghanim M. Predicting pavement condition index using artificial neural networks approach. Ain Shams Engineering Journal 2022;13. https://doi.org/10.1016/j.asej.2021.04.033.
[11] Sirhan M, Bekhor S, Sidess A. Implementation of Deep Neural Networks for Pavement Condition Index Prediction. Journal of Transportation Engineering, Part B: Pavements 2022;148. https://doi.org/10.1061/jpeodx.0000333.
[12] Mahmood M, Anuraj U, Mathavan S, Rahman M. A unified artificial neural network model for asphalt pavement condition prediction. Proceedings of the Institution of Civil Engineers: Transport 2023;176. https://doi.org/10.1680/jtran.19.00111.
[13] Boonsiripant S, Athan C, Jedwanna K, Lertworawanich P, Sawangsuriya A. Comparative Analysis of Deep Neural Networks and Graph Convolutional Networks for Road Surface Condition Prediction. Sustainability 2024;16:9805. https://doi.org/10.3390/su16229805.
[14] Sharma A, Aggarwal P. IRI Prediction Using Machine Learning Models. Wseas Transactions on Computer Research 2023;11:111–6. https://doi.org/10.37394/232018.2023.11.10.
[15] Bashar MZ, Torres-Machi C. Performance of machine learning algorithms in predicting the pavement international roughness index. Transp Res Rec 2021;2675:226–37.
[16] Radwan MM, Mousa A, Zahran EMM. Enhancing Pavement Sustainability: Prediction of the Pavement Condition Index in Arid Urban Climates Using the International Roughness Index. Sustainability (Switzerland) 2024;16. https://doi.org/10.3390/su16083158.
[17] Molinero-Pérez N, Montalbán-Domingo L, Sanz-Benlloch A, García-Segura T. Dual Model for International Roughness Index Classification and Prediction. Infrastructures (Basel) 2025;10:23. https://doi.org/10.3390/infrastructures10010023.
[18] Ghavami S, Naseri H, Jahanshahi FS. Enhanced Prediction and Uncertainty Modeling of Pavement Roughness Using Machine Learning and Conformal Prediction. Infrastructures (Basel) 2025;10:166. https://doi.org/10.3390/infrastructures10070166.
[19] Ibrahim RA, Elsheikh AH, Elasyed Abd Elaziz M, Al-qaness MAA. Chapter one - Basics of artificial neural networks. In: Elsheikh AH, Abd Elaziz ME, editors. Artificial Neural Networks for Renewable Energy Systems and Real-World Applications, Academic Press; 2022, p. 1–10. https://doi.org/https://doi.org/10.1016/B978-0-12-820793-2.00002-1.
[20] Sigdel T, Pradhananga R, Shrestha S. Artificial Neural Network-based model to predict the International Roughness Index of national highways in Nepal. Transp Res Interdiscip Perspect 2024;25. https://doi.org/10.1016/j.trip.2024.101128.
[21] Sharma A, Sachdeva SN, Aggarwal P. Predicting IRI Using Machine Learning Techniques. International Journal of Pavement Research and Technology 2023;16. https://doi.org/10.1007/s42947-021-00119-w.
[22] Wang C, Xu S, Yang J. Adaboost Algorithm in Artificial Intelligence for Optimizing the IRI Prediction Accuracy of Asphalt Concrete Pavement. Sensors 2021;21:5682. https://doi.org/10.3390/s21175682.
[23] Abaza KA. The Use of IRI Data in Developing Optimal Pavement Rehabilitation Plan for Developing Countries: Palestine as a Case Study 2023. https://doi.org/10.21203/rs.3.rs-3247799/v1.
[24] Rifai M. Evaluation of Functional and Structural Conditions on Flexible Pavements Using Pavement Condition Index (PCI) and International Roughness Index (IRI) Methods. E3s Web of Conferences 2023;429:05011. https://doi.org/10.1051/e3sconf/202342905011.
[25] Chen K, Torbaghan ME, Thom N, Faramarzi A. Physics-guided neural network for predicting international roughness index on flexible pavements considering accuracy, uncertainty and stability. Eng Appl Artif Intell 2025;142. https://doi.org/10.1016/j.engappai.2024.109922.
[26] Chen L, Li H, Wang S, Shan F, Han Y, Zhong G. Imporved model for pavement performance prediction based on recurrent neural network using LTPP database. International Journal of Transportation Science and Technology 2024. https://doi.org/10.1016/j.ijtst.2024.08.005.
[27] Kwon K, Choi H, Pham K, Kim S, Bae A. Influence Analysis of Pavement Distress on International Roughness Index Using Machine Learning. KSCE Journal of Civil Engineering 2024. https://doi.org/10.1007/s12205-024-0093-9.
[28] Oktopianto Y, Antonius A, Rochim A. An Artificial Neural Network Approach for Predicting Pavement Distress: A Case Study Toward Sustainable Road Maintenance. Advance Sustainable Science, Engineering and Technology (ASSET) 2025;7. https://doi.org/10.26877/asset.v7i3.2133.
[29] Ali AA, Esekbi M, Sreh M. Development of International Roughness Index From Pavement Distress Using Artificial Neural Networks (ANNs). International Journal of Advanced Engineering and Business Sciences 2023;4:179–92. https://doi.org/10.21608/ijaebs.2023.165192.1054.
[30] Plati C, Armeni A, Kyriakou C, Asoniti D. AI for Predicting Pavement Roughness in Road Monitoring and Maintenance. Infrastructures (Basel) 2025;10. https://doi.org/10.3390/infrastructures10070157.
[31] Sun Y, Gao Q, Li F, Du Y. Distress-Level Prediction of Pavement Deterioration with Causal Analysis and Uncertainty Quantification. Applied Sciences (Switzerland) 2025;15. https://doi.org/10.3390/app152011250.
[32] Famewo BG, Shokouhian M. A Review of Pavement Performance Deterioration Modeling: Influencing Factors and Techniques. Symmetry (Basel) 2025;17. https://doi.org/10.3390/sym17111992.
[33] Afridi MA, Erlingsson S. Enhancing municipal pavement condition predictions using machine learning models. Journal of Road Engineering 2026. https://doi.org/10.1016/j.jreng.2025.10.002.
[34] Basnet KS, Shrestha J, Shrestha R. Artificial Neural Networks and Multiple Linear Regression in Pavement Deterioration Forecasting. Journal on Transportation System and Engineering 2025;1. https://doi.org/10.3126/jotse.v1i2.87728.
[35] Rosada A, Arliansyah J, Buchari E. Evaluation Pavement Deteriorating Condition on Surface Distress Index (SDI) Data Using Radial Basis Function Neural Networks (RBFNN). J. Phys. Conf. Ser., vol. 1198, 2019. https://doi.org/10.1088/1742-6596/1198/3/032008.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Advance Sustainable Science Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
