Impacts of Increased Prediction Accuracy in Management Decisions: A Study of Full-Depth Reclamation Pavements
Publication: Journal of Infrastructure Systems
Volume 30, Issue 1
Abstract
Given the abundance of condition data regularly collected for major roadways, machine learning has the potential to enhance pavement deterioration modeling. This is particularly important for recycling-based rehabilitation techniques, such as full-depth reclamation (FDR), which lack accurate models of deterioration. Previous studies have demonstrated the effectiveness of machine learning (ML) to predict pavement deterioration. However, the increased accuracy of these models often is reported using statistical metrics that pavement managers cannot easily relate to asset management decision-making. This paper quantifies the impacts that increased accuracies in deterioration modeling have on relevant metrics used in the management of pavement assets. The study analyzed the performance of full-depth-reclamation pavements and developed random forest models to estimate roughness, rutting, and fatigue cracking. These random forest models were compared with mechanistic-empirical (M-E) models tuned to the same sites to quantify differences in prediction accuracy, useful life, life-cycle costs, and long-term performance. The tuned random forest deterioration models reduced errors by 90%–97% compared with the tuned M-E models. The results suggest that M-E predicts that FDR reaches the end of service life 8 years sooner than do the random forest predictions. The long-term performance of FDR was found to be 28%–73% higher in a 10-year design life than M-E models predict. This indicates that FDR is significantly more cost-effective than is presumed by M-E predictions, and that improvements in the accuracy of FDR predictions may result in more-informed decision-making.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
All data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
The authors acknowledge the financial support from the Colorado Department of Transportation to develop this study (Study No. R421.01, “Life-Cycle Cost and Sensitivity Analysis of Pavement Rehabilitation Alternatives”). The financial support of the first author through the United States Department of Education Graduate Assistance in Areas of National Need Grant P200A210013 is gratefully acknowledged.
References
AASHTO. 2020. Mechanistic-empirical pavement design guide. Washington, DC: AASHTO.
Ahmed, N. S., and M. Hikmat Sadiq. 2018. Clarify of the random forest algorithm in an educational field, 179–184. New York: IEEE. https://doi.org/10.1109/ICOASE.2018.8548804.
Al-Mosawe, H. 2016. “Prediction of permanent deformation in asphalt mixtures.” Ph.D. thesis, Dept. of Civil Engineering, Univ. of Nottingham.
Al-Qadi, I. L., T. Scarpas, and A. Loizos. 2008. Pavement cracking: Mechanisms, modeling, detection, testing and case histories. Boca Raton, FL: CRC Press.
Amarh, E. A., J. Santos, G. W. Flintsch, and B. K. Diefenderfer. 2022. “Evaluating the potential environmental benefits of cold recycling-based methods for flexible pavement rehabilitation in Virginia.” Transp. Res. Rec. 2676 (6): 75–86. https://doi.org/10.1177/03611981211072786.
Archilla, A. R., and S. Madanat. 2000. “Development of a pavement rutting model from experimental data.” J. Transp. Eng. 126 (4): 291–299. https://doi.org/10.1061/(ASCE)0733-947X(2000)126:4(291).
Asphalt Recycling and Reclaiming Association, and L. Dunn. 2001. Basic asphalt recycling manual. Annapolis, MD: Asphalt Recycling and Reclaiming Association.
Attoh-Okine, N. O. 1994. Predicting roughness progression in flexible pavements using artificial neural networks. Washington, DC: Transportation Research Board.
Bai, Y., O. E. Gungor, J. A. Hernandez-Urrea, Y. Ouyang, and I. L. Al-Qadi. 2015. “Optimal pavement design and rehabilitation planning using a mechanistic-empirical approach.” EURO J. Transp. Logist. 4 (1): 57–73. https://doi.org/10.1007/s13676-014-0072-2.
Bairgi, B. K., R. A. Tarefder, M. Amanul Hasan, M. M. Hasan, M. A. Gburi, and Z. Khan. 2022. “Evaluation of full-depth reclamation and cold central-plant recycling mixtures for laboratory compaction, mechanistic response, and performance properties.” Transp. Res. Rec. 2676 (5): 779–792. https://doi.org/10.1177/03611981211070551.
Bashar, M. Z., and C. Torres-Machi. 2021. “Performance of machine learning algorithms in predicting the pavement international roughness index.” Transp. Res. Rec. 2675 (5): 226–237. https://doi.org/10.1177/0361198120986171.
Bashar, M. Z., and C. Torres-Machi. 2023. “Machine learning to enhance the management of highway pavements and bridges.” Infrastruct. Asset Manage. https://doi.org/10.1680/jinam.22.00031.
Beesam, V. V., and C. Torres-Machi. 2021. “Input parameters for the mechanistic-empirical design of full-depth reclamation projects.” Transp. Res. Rec. 2675 (11): 384–396. https://doi.org/10.1177/03611981211017916.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324.
Caltrans. 2008. “Maintenance technical advisory guide (MTAG).” Accessed June 19, 2023. https://dot.ca.gov/programs/maintenance/pavement/mtag.
Cano-Ortiz, S., P. Pascual-Muñoz, and D. Castro-Fresno. 2022. “Machine learning algorithms for monitoring pavement performance.” Autom. Constr. 139 (Mar): 104309. https://doi.org/10.1016/j.autcon.2022.104309.
CDOT (Colorado Department of Transportation). 2021. “2021 CDOT M-E pavement design manual.” Accessed December 2, 2022. https://www.codot.gov/business/designsupport/materials-and-geotechnical/manuals/2021-m-e-pave-design-manual.
de la Garza, J. M., S. Akyildiz, D. R. Bish, and D. A. Krueger. 2011. “Network-level optimization of pavement maintenance renewal strategies.” Adv. Eng. Inf. 25 (4): 699–712. https://doi.org/10.1016/j.aei.2011.08.002.
Diefenderfer, B. K., and A. K. Apeagyei. 2011. Analysis of full-depth reclamation trial sections in Virginia. Charlottesville, VA: Virginia Center for Transportation Innovation and Research.
Evers, E., M. Z. Bashar, and C. Torres-Machi. 2023a. Improving the prediction of full-depth reclamation pavements performance using random forests. Washington, DC: Transportation Research Board of the National Academies.
Evers, E., A. Shrestha, E. Garcia, M. Bashar, C. Torres-Machi, K. Choi, and Y. Zhang. 2023b. Machine learning rutting model for sustainable pavement rehabilitation. Moncton, NB: Canadian Society of Civil Engineers.
Farashah, M. K., S. Salehiashani, S. Varamini, and S. Tighe. 2021. Best practices in measuring rutting and shoving on asphalt pavements. Ottawa: Transportation Associated of Canada.
FHWA (Federal Highway Administration). 1998. Life-cycle cost analysis in pavement design. Washington, DC: FHWA.
FHWA (Federal Highway Administration). 2016. “Highway performance monitoring system field manual.” Accessed December 23, 2022. https://www.fhwa.dot.gov/policyinformation/hpms/fieldmanual/.
FHWA (Federal Highway Administration). 2021. “LTPP climate tool.” Accessed July 16, 2022. https://infopave.fhwa.dot.gov/Data/ClimateTool.
Gong, H., Y. Sun, W. Hu, P. A. Polaczyk, and B. Huang. 2019. “Investigating impacts of asphalt mixture properties on pavement performance using LTPP data through random forests.” Constr. Build. Mater. 204 (Apr): 203–212. https://doi.org/10.1016/j.conbuildmat.2019.01.198.
Gong, H., Y. Sun, X. Shu, and B. Huang. 2018. “Use of random forests regression for predicting IRI of asphalt pavements.” Constr. Build. Mater. 189 (Nov): 890–897. https://doi.org/10.1016/j.conbuildmat.2018.09.017.
Google. 2022. “Decision forests.” Accessed December 23, 2022. https://developers.google.com/machine-learning/decision-forests/out-of-bag.
Gu, F., W. Ma, R. C. West, A. J. Taylor, and Y. Zhang. 2019. “Structural performance and sustainability assessment of cold central-plant and in-place recycled asphalt pavements: A case study.” J. Cleaner Prod. 208 (Jan): 1513–1523. https://doi.org/10.1016/j.jclepro.2018.10.222.
Guo, R., D. Fu, and G. Sollazzo. 2021. “An ensemble learning model for asphalt pavement performance prediction based on gradient boosting decision tree.” Int. J. Pavement Eng. 22 (1): 1–10. https://doi.org/10.1080/10298436.2021.1910825.
Haddad, A. J., G. R. Chehab, and G. A. Saad. 2022. “The use of deep neural networks for developing generic pavement rutting predictive models.” Int. J. Pavement Eng. 23 (12): 4260–4276. https://doi.org/10.1080/10298436.2021.1942466.
Hasan, M. M., A. S. M. A. Rahman, and R. A. Tarefder. 2020. “Investigation of accuracy of pavement mechanistic empirical prediction performance by incorporating Level 1 inputs.” J. Traffic Transp. Eng. 7 (2): 259–268. https://doi.org/10.1016/j.jtte.2018.06.006.
Hong, F., and J. A. Prozzi. 2015. “Pavement deterioration model incorporating unobserved heterogeneity for optimal life-cycle rehabilitation policy.” J. Infrastruct. Syst. 21 (1): 04014027. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000168.
Hosseini, S. A., and O. Smadi. 2021. “How prediction accuracy can affect the decision-making process in pavement management system.” Infrastructures 6 (2): 28. https://doi.org/10.3390/infrastructures6020028.
Howard, I. L., and B. C. Cox. 2016. “Multiyear laboratory and field performance assessment of high-traffic US-49 full-depth reclamation.” Transp. Res. Rec. 2573 (1): 86–97. https://doi.org/10.3141/2573-11.
James, G., D. Witten, T. Hastie, and R. Tibshirani. 2013. “An introduction to statistical learning: With applications in R.” Accessed December 3, 2022. https://link.springer.com/book/10.1007/978-1-4614-7138-7.
Justo-Silva, R., A. Ferreira, and G. Flintsch. 2021. “Review on machine learning techniques for developing pavement performance prediction models.” Sustainability 13 (9): 5248. https://doi.org/10.3390/su13095248.
Kaya, O. 2015. “Investigation of AASHTOWare pavement ME Design/Darwin-METM performance prediction models for Iowa pavement analysis and design.” Master of Science thesis, Dept. of Civil, Construction, and Environmental Engineering, Iowa State Univ., Digital Repository.
Khurshid, M. B., M. Irfan, and S. Labi. 2009. “Comparison of methods for evaluating pavement interventions: Evaluation and case study.” Transp. Res. Rec. 2108 (1): 25–36. https://doi.org/10.3141/2108-03.
Labi, S. 2014. Introduction to civil engineering systems: A systems perspective to the development of civil engineering facilities. New York: Wiley.
Luo, X., F. Wang, S. Bhandari, N. Wang, and X. Qiu. 2021. “Effectiveness evaluation and influencing factor analysis of pavement seal coat treatments using random forests.” Constr. Build. Mater. 282 (May): 122688. https://doi.org/10.1016/j.conbuildmat.2021.122688.
Majidifard, H., B. Jahangiri, P. Rath, A. H. Alavi, and W. G. Buttlar. 2021. “A deep learning approach to predict Hamburg rutting curve.” Road Mater. Pavement Des. 22 (9): 2159–2180. https://doi.org/10.1080/14680629.2021.1886160.
Marcelino, P., M. de Lurdes Antunes, E. Fortunato, and M. C. Gomes. 2021. “Machine learning approach for pavement performance prediction.” Int. J. Pavement Eng. 22 (3): 341–354. https://doi.org/10.1080/10298436.2019.1609673.
Melese, E., H. Baaj, G. Maria Dias, and S. Tighe. 2022. “Effects of cementitious stabilisers on performance and life cycle impacts of full-depth reclamation.” Road Mater. Pavement Des. 24 (5): 1353–1370. https://doi.org/10.1080/14680629.2022.2072375.
Piryonesi, S. M., and T. E. El-Diraby. 2020. “Data analytics in asset management: Cost-effective prediction of the pavement condition index.” J. Infrastruct. Syst. 26 (1): 04019036. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000512.
Piryonesi, S. M., and T. E. El-Diraby. 2021. “Using machine learning to examine impact of type of performance indicator on flexible pavement deterioration modeling.” J. Infrastruct. Syst. 27 (2): 04021005. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000602.
Prozzi, J. A. 2001. “Modeling pavement performance by combining field and experimental data.” Ph.D. dissertation, Dept. of Civil and Environmental Engineering, Univ. of California.
Qiao, Y., S. Chen, M. Alinizzi, M. Alamaniotis, and S. Labi. 2022. “IRI estimation based on pavement distress type, density, and severity: Efficacy of machine learning and statistical techniques.” J. Infrastruct. Syst. 28 (4): 04022035. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000718.
Reeder, G. D., D. S. Harrington, M. E. Ayers, and W. Adaska. 2017. Guide to full-depth reclamation (FDR) with cement. Washington, DC: Transportation Research Board.
Rogers, J., and S. Gunn. 2006. “Identifying feature relevance using a random forest.” In Subspace, latent structure and feature selection, lecture notes in computer science, edited by C. Saunders, M. Grobelnik, S. Gunn, and J. Shawe-Taylor, 173–184. Berlin: Springer.
Sayers, M. W., T. D. Gillespie, and W. D. O. Paterson. 1986. “Guidelines for conducting and calibrating road roughness measurements.” In World Bank technical paper. Washington, DC: World Bank.
Schwartz, C. W., B. K. Diefenderfer, and B. F. Bowers. 2017. Material properties of cold in-place recycled and full-depth reclamation asphalt concrete. Washington, DC: Transportation Research Board.
Sharma, A., S. N. Sachdeva, and P. Aggarwal. 2021. “Predicting IRI using machine learning techniques.” Int. J. Pavement Res. Technol. 16 (1): 1–10. https://doi.org/10.1007/s42947-021-00119-w.
Smith, S., and A. Braham. 2018. “Comparing layer types for the use of PavementME for asphalt emulsion full depth reclamation design.” Constr. Build. Mater. 158 (Jan): 481–489. https://doi.org/10.1016/j.conbuildmat.2017.10.054.
Szepesvári, C. 2010. “Algorithms for reinforcement learning.” In Vol. 4 of Synthesis lectures on artificial intelligence and machine learning, 1–103. New York: Springer.
Uddin, W., W. R. Hudson, and R. Haas. 2013. Public infrastructure asset management. New York: McGraw-Hill.
Uwanuakwa, I. D., S. I. A. Ali, M. R. M. Hasan, P. Akpinar, A. Sani, and K. A. Shariff. 2020. “Artificial intelligence prediction of rutting and fatigue parameters in modified asphalt binders.” Appl. Sci. 10 (21): 7764. https://doi.org/10.3390/app10217764.
Yepes, V., C. Torres-Machi, A. Chamorro, and E. Pellicer. 2016. “Optimal pavement maintenance programs based on a hybrid greedy randomized adaptive search procedure algorithm.” J. Civ. Eng. Manage. 22 (4): 540–550. https://doi.org/10.3846/13923730.2015.1120770.
Zhao, J., and H. Wang. 2021. “Mechanistic-empirical analysis of asphalt pavement fatigue cracking under vehicular dynamic loads.” Constr. Build. Mater. 284 (May): 122877. https://doi.org/10.1016/j.conbuildmat.2021.122877.
Zimmerman, K. A., and D. G. Peshkin. 2004. “Issues in integrating pavement management and preventive maintenance.” Transp. Res. Rec. 1889 (1): 13–20. https://doi.org/10.3141/1889-02.
Information & Authors
Information
Published In
Journal of Infrastructure Systems
Volume 30 • Issue 1 • March 2024
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Jul 25, 2023
Accepted: Oct 22, 2023
Published online: Nov 16, 2023
Published in print: Mar 1, 2024
Discussion open until: Apr 16, 2024
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Asset management
- Business management
- Computer programming
- Computing in civil engineering
- Deterioration
- Ecosystems
- Engineering fundamentals
- Environmental engineering
- Errors (statistics)
- Financial management
- Forests
- Gravels
- Highway and road management
- Highway transportation
- Infrastructure
- Materials characterization
- Materials engineering
- Mathematics
- Model accuracy
- Models (by type)
- Pavement condition
- Pavements
- Practice and Profession
- Statistics
- Transportation engineering
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.