Predictive modeling of punchouts in continuously reinforced concrete pavement: a machine learning approach

Abstract

The accurate prediction of the deterioration of Continuously Reinforced Concrete Pavement (CRCP) is essential for the effective management of pavements and the maintenance of infrastructure. In this study, a comprehensive approach that integrates descriptive statistics, correlation analysis, and machine learning algorithms is employed to develop models and predict punchouts in CRCP. The dataset used in this study is extracted from the Long-Term Pavement Performance (LTPP) database and contains a wide range of pavement attributes, such as age, climate zone, thickness, and traffic data. Initial exploratory analysis reveals varying distributions among the input features, which serves as the foundation for subsequent analysis. A correlation heatmap matrix is utilized to elucidate the relationships between these attributes and punchouts, guiding the selection of features for modeling. By employing the random forest algorithm, key predictors like age, climate zone, and total thickness are identified. Various machine learning techniques, encompassing linear regression, decision trees, support vector machines, ensemble methods, Gaussian process regression, artificial neural networks, and kernel-based approaches, are compared. It is noteworthy that ensemble methods such as boosted trees and Gaussian process regression models exhibit promising predictive performance, with low root mean square error (RMSE) and high R-squared values. The outcomes of this study provide valuable insights for the development of pavement management strategies, facilitating informed decision-making regarding resource allocation and infrastructure maintenance. Future research could focus on refining models, exploring additional features, and validating results through real-world implementation trials. This study contributes to advancing predictive modeling techniques for optimizing CRCP infrastructure management and durability.

Keywords

Support vector machine / Gaussian process regression / Ensemble learning / Random forest / Artificial neural network / Artificial intelligence-driven pavement condition assessment / Information and Computing Sciences / Artificial Intelligence and Image Processing / Mathematical Sciences / Statistics

References

[1] AgunwambaJC, TizaMT. An appraisal of mechanistic-empirical models (MEMs) in pavement deterioration. Journal of Nature, 2023, 2: 6855

[2] Al-KhateebGG, AlnaqbiA, ZeiadaW. Statistical and machine learning models for predicting spalling in CRCP. Scientific Reports, 2024, 14121301.

[3] AlnaqbiA, Al-KhateebG, ZeiadaW. A hybrid approach of support vector regression with genetic algorithm optimization for predicting spalling in continuously reinforced concrete pavement. Journal of Building Pathology and Rehabilitation, 2024, 92146.

[4] AlnaqbiA, Al-KhateebGG, ZeiadaW. Predictive modeling of transverse cracking in continuously reinforced concrete pavement: A machine learning approach. Engineering Research Express, 2025, 71015106.

[5] AlnaqbiA, Al-KhateebGG, ZeiadaW, NasrE, AbuzwidahM. Machine learning applications for predicting faulting in jointed reinforced concrete pavement. Arabian Journal for Science and Engineering, 2024.

[6] AlnaqbiAJ, ZeiadaW, Al-KhateebG, AbttanA, AbuzwidahM. Predictive models for flexible pavement fatigue cracking based on machine learning. Transportation Engineering, 2024, 16: 100243.

[7] AlnaqbiA, ZeiadaW, Al-KhateebGG, AbuzwidahM. Machine learning modeling of wheel and non-wheel path longitudinal cracking. Buildings, 2024, 143709.

[8] AlnaqbiAJ, ZeiadaW, Al-KhateebGG, HamadK, BarakatS. Creating rutting prediction models through machine learning techniques utilizing the long-term pavement performance database. Sustainability, 2023, 151813653.

[9] AlqaydiS, ZeiadaW, El WakilA, AlnaqbiAJ, AzamA. A Comprehensive review of smartphone and other device-based techniques for road surface monitoring. Eng, 2024, 543397-3426.

[10] Al-SamahiS, ZeiadaW, Al-KhateebGG, HamadK, AlnaqbiA. A comparative study of pavement roughness prediction models under different climatic conditions. Infrastructures, 2024.

[11] Bayomy, F., Muftah, A., Kassem, E., Williams, C., & Hasnat, M. (2019). Calibration of the AASHTOWare Pavement ME Design Software for PCC Pavements in Idaho (No. FHWA-ID-19–268). Idaho. Transportation Department.‏

[12] BenmokraneB, Sanni BakoureguiA, MohamedHM, ThébeauD, AbdelkarimOI. Design, construction, and performance of continuously reinforced concrete pavement reinforced with GFRP bars: Case study. Journal of Composites for Construction, 2020, 24505020004.

[13] Cano-OrtizS, Pascual-MuñozP, Castro-FresnoD. Machine learning algorithms for monitoring pavement performance. Automation in Construction, 2022, 139: 104309.

[14] Corley-Lay, J., O'Doherty, J., Hooks, J., & Scofield, L. (2020). Federal Highway Administration (FHWA) Pavement Preservation Research Roadmap (No. FHWA-HIF-20–070). United States. Federal Highway Administration. Office of Pavement Technology.‏

[15] Federal Highway Administration. (2003). Distress identification manual for the long-term pavement performance program (Publication No. FHWA-RD-03–031). U.S. Department of Transportation. https://www.fhwa.dot.gov/publications/research/infrastructure/pavements/ltpp/reports/03031/03031.pdf

[16] FyhrieP, RavaniB, JiAPerformance measures for roadside features (No. CA19–2761), 2018Department of Transportation

[17] GopalakrishnanK. Deep learning in data-driven pavement image analysis and automated distress detection: A review. Data, 2018, 3328.

[18] GuoJ, ChanTM, WangY. Precast concrete pavement applications, design and joint load transfer characteristics. Structures, 2024, 69: 107176.

[19] IoannidesAM, TallapragadaPK. An overview and a case study of pavement performance prediction. International Journal of Pavement Engineering, 2013, 147629-644.

[20] KochC, ZhuZ, German PaalS, BrilakisI. Machine vision techniques for condition assessment of civil infrastructure. Integrated Imaging and Vision Techniques for Industrial Inspection: Advances and Applications, 2015.

[21] KyriazosT, PogaM. Application of machine learning models in social sciences: Managing nonlinear relationships. Encyclopedia, 2024, 441790-1805.

[22] MarchettySReduction of transverse cracking in structural slab bridge decks using alternative materials, 2018University of Akron

[23] MukhopadhyayAK, ShiX, ZollingerDGRecycling and reuse of materials in transportation projects-current status and potential opportunities including evaluation of RCA concrete pavements along an Oklahoma interstate highway (No. FHWA-OK-18–04), 2018Department of Transportation

[24] MunawarHS, HammadAW, WallerST, IslamMR. Modern crack detection for bridge infrastructure maintenance using machine learning. Human-Centric Intelligent Systems, 2022, 2395-112.

[25] PlevrisV, PapazafeiropoulosG. AI in structural health monitoring for infrastructure maintenance and safety. Infrastructures, 2024, 912225.

[26] RagnoliA, De BlasiisMR, Di BenedettoA. Pavement distress detection methods: A review. Infrastructures, 2018, 3458.

[27] Rane, N., Choudhary, S., & Rane, J. (2024). Integrating deep learning with machine learning: technological approaches, methodologies, applications, opportunities, and challenges. Available at SSRN 4850000.‏

[28] RaneNL, ParameshaM, ChoudharySP, RaneJ. Machine learning and deep learning for big data analytics: A review of methods and applications. Partners Universal International Innovation Journal, 2024, 23172-197

[29] RoeslerJR, HillerJE, BrandASContinuously reinforced concrete pavement manual, guidelines for design, construction, maintenance, and rehabilitation (No FHWA-HIF-16–026), 2016Federal Highway Administration

[30] RuizJM, RasmussenRO, ChangGK, DickJC, NelsonPK, SchindlerAK, WildeWJComputer-based guidelines for concrete pavements: volume III technical appendices (No FHWA-HRT-04–127), 2006Turner-Fairbank Highway Research Center

[31] SallesLSDShort continuously reinforced concrete pavement design recommendations based on non-destructive ultrasonic data and stress simulation, 2017Universidade de São Paulo.

[32] ShomeA, MukherjeeG, ChatterjeeA, TuduBMallikBB, MukherjeeG, KarR, ChaudharyA. Study of different regression methods, models and application in deep learning paradigm. Deep learning concepts in operations research, 2024Auerbach Publications130-152.

[33] SmitMSResponse of ultra-thin continuously reinforced concrete pavement to traffic loading, 2020University of Pretoria

[34] SmithKD, SignoreJ, TompkinsD, RamPImplementation of composite pavement systems (No. FHWA-HIF-19–014), 2019Federal Highway Administration

[35] TamaguskoT, Gomes CorreiaM, FerreiraA. Machine learning applications in road pavement management: A review, challenges and future directions. Infrastructures, 2024.

[36] Yaqoob, S. (2022). Report on 12th International Conference on Concrete Pavements: “Making Waves with Durable and Resilient Concrete Pavements”.‏

[37] ZeiadaW, AlnaqbiAJ, Al-KhateebGG, AbuzwidahM. Machine learning modeling of transverse cracking in flexible pavement. Discover Civil Engineering, 2024, 111-26.

RIGHTS & PERMISSIONS

The Author(s)