Machine Learning-Based Prediction of International Roughness Index for Continuous Reinforced Concrete Pavements

Ragaa T. Abd El-Hakim, Associate Professor, Public Works Engineering Department, Faculty of Engineering, Tanta University, Tanta, EgyptFollow
Ahmed N. Awaad, Graduate Research Assistant, Public Works Engineering Department, Faculty of Engineering, Mansoura University, Mansoura 35516, Egypt
Sherif M. El-Badawy, Professor, Highway & Airport Engineering Laboratory, Public Works Engineering Department, Faculty of Engineering, Mansoura University, Mansoura 35516, Egypt

Subject Area

Civil and Environmental Engineering

Article Type

Original Study

Abstract

The International Roughness Index (IRI) serves as a crucial indicator for ride quality and user comfort. As road roughness escalates, road serviceability diminishes, resulting in reduced vehicle speed and increased travel time, and consequently higher carbon dioxide emissions. Predicting the IRI is of utmost importance for Pavement Management Systems and sustainable development overall. While numerous studies have forecasted the IRI of flexible pavements, there is a notable scarcity of research focusing on rigid pavement performance prediction. This study addresses the gap in predicting IRI for Continuous Reinforced Concrete Pavements (CRCP), an understudied aspect of pavement engineering. Leveraging the Long-Term Pavement Performance (LTPP) database, different machine learning (ML) techniques were applied to different input parameter representation. There are 90 measurements for the data points of the International Roughness Index (IRI). The input variables include the initial IRI, counts of medium- and high-severity transverse cracks, counts of medium- and high-severity punchouts, the percentage of pavement surface with patching (ranging from medium to high severity in both flexible and rigid pavements), pavement age, freezing index, and the percentage of subgrade material passing through the No. 200 U.S. sieve. Through data analysis and ML algorithms, an accurate IRI prediction model for CRCP pavements is developed. The results of this study show that the Adaptive boosting algorithm (AdaBoost) model for CRCP yielded very good prediction accuracy (R2=0.90, and 0.83 for training and testing datasets respectively) with low bias. The study findings offer valuable insights into CRCP IRI prediction, benefiting pavement management and maintenance strategies.

Keywords

IRI, Machine Learning, CRCP, Modelling, Transverse Cracks, AdaBoost, Ensemble Learning

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 License.

Recommended Citation

El-Hakim, Ragaa T. Abd; Awaad, Ahmed N.; and El-Badawy, Sherif M. (2024) "Machine Learning-Based Prediction of International Roughness Index for Continuous Reinforced Concrete Pavements," Mansoura Engineering Journal: Vol. 49 : Iss. 3 , Article 14.
Available at: https://doi.org/10.58491/2735-4202.3195

Download