Machine Learning–Based Framework for Prediction of Retroreflectivity Degradation of Pavement Markings across the US
Publication: Journal of Transportation Engineering, Part B: Pavements
Volume 150, Issue 2
Abstract
Pavement markings are essential traffic control devices that enhance safety for motorists during nighttime. Numerous statistical learning models have been developed in prior studies to predict the retroreflectivity of the markings, but the applicability of these models is questionable in terms of accuracy. The key objective of this study was to develop a machine learning–based framework that can be used by US transportation agencies to reliably predict the retroreflectivity of their pavement markings over a period of 3 years utilizing the initially measured retroreflectivity and other key project conditions. The random forest (RF) algorithm was used in this study to develop the proposed framework considering seven types of marking materials in three different US climate zones. A total of 49,632 transverse skip retroreflectivity measurements were retrieved from the National Transportation Product Evaluation Program (NTPEP) and 11 RF models were developed to sequentially predict retroreflectivity at different prediction horizons. The models were trained with randomly selected 80% of the total data points, and the remaining 20% data points were utilized for testing the predictive performance of the developed models. The RF models predicted the retroreflectivity with a superior level of accuracy ( ranging between 0.88 and 0.99) than the models proposed in prior studies. These models are expected to aid transportation agencies in reliably determining the effective service lives of their marking products.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
All data, models, and code generated or used during the study appear in the published article.
Acknowledgments
The financial support of the National Cooperative Highway Research Program (NCHRP) is greatly appreciated. This study is part of the NCHRP IDEA project (Project No. 20-30/IDEA 237).
References
Abboud, N., and B. L. Bowman. 2002. “Cost-and longevity-based scheduling of paint and thermoplastic striping.” Transp. Res. Rec. 1794 (1): 55–62. https://doi.org/10.3141/1794-07.
ASTM. 2017. Standard practice for conducting road service tests on fluid traffic marking materials. ASTM D713-12. West Conshohocken, PA: ASTM.
Benesty, J., J. Chen, and Y. Huang. 2008. “On the importance of the Pearson correlation coefficient in noise reduction.” IEEE Trans. Audio Speech Lang. Process. 16 (4): 757–765. https://doi.org/10.1109/TASL.2008.919072.
Breiman, L. 2001. “Random forests.” Mach. Learn. 45 (1): 5–32. https://doi.org/10.1023/A:1010933404324.
Elwakil, E., A. Eweda, and T. Zayed. 2014. “Modelling the effect of various factors on the condition of pavement marking.” Struct. Infrastruct. Eng. 10 (1): 93–105. https://doi.org/10.1080/15732479.2012.701650.
Elyan, E., and M. M. Gaber. 2017. “A genetic algorithm approach to optimising random forests applied to class engineered data.” Info. Sci. 384 (Apr): 220–234. https://doi.org/10.1016/j.ins.2016.08.007.
Fitch, J. M., and W. E. Ahearn. 2007. Pavement marking durability statewide final report. Montpelier, VT: Materials and Research Section, State of Vermont Agency of Transportation.
Fu, H., and C. G. Wilmot. 2013. “Evaluating alternative pavement marking materials.” Public Works Manage. Policy 18 (3): 279–297. https://doi.org/10.1177/1087724X12451844.
Idris, I. I., M. R. Mousa, M. Hassan, and H. Dhasmana. 2022. “Predicting the retroreflectivity degradation of thermoplastic pavement markings with genetic algorithm.” In Proc., 2022 Tran-SET Conf., 146–155. Reston, VA: ASCE.
James, G., D. Witten, T. Hastie, and R. Tibshirani. 2021. An introduction to statistical learning. New York: Springer.
Jorge, I. 2011. “The influence of the E-Tutor on the development of collaborative critical thinking in a students’ E-Forum: Association levels with Cramer’s V.” In Proc., Int. Council for Educational Media and the XIII Int. Symp. on Computers in Education (ICEMandSIIE’2011) Joint Conference: Old Meets New: Media in Education, 287–296. Aveiro, Portugal: Univ. of Aveiro.
Karballaeezadeh, N., H. Ghasemzadeh Tehrani, D. Mohammadzadeh Shadmehri, and S. Shamshirband. 2020a. “Estimation of flexible pavement structural capacity using machine learning techniques.” Front. Struct. Civ. Eng. 14 (Oct): 1083–1096. https://doi.org/10.1007/s11709-020-0654-z.
Karballaeezadeh, N., S. D. Mohammadzadeh, D. Moazemi, S. S. Band, A. Mosavi, and U. Reuter. 2020b. “Smart structural health monitoring of flexible pavements using machine learning methods.” Coatings 10 (11): 1100. https://doi.org/10.3390/coatings10111100.
Karwa, V., and E. T. Donnell. 2011. “Predicting pavement marking retroreflectivity using artificial neural networks: Exploratory analysis.” J. Transp. Eng. 137 (2): 91–103. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000194.
Kopf, J. 2004. Reflectivity of pavement markings: Analysis of retroreflectivity curves. Seattle: Washington State Transportation Center, Univ. of Washington.
Lee, J. T., T. L. Maleck, and W. C. Taylor. 1999. “Pavement making material evaluation study in Michigan.” ITE J. 69 (7): 44.
Liang, L., L. Di, T. Huang, J. Wang, L. Lin, L. Wang, and M. Yang. 2018. “Estimation of leaf nitrogen content in wheat using new hyperspectral indices and a random forest regression algorithm.” Remote Sens. 10 (12): 1940. https://doi.org/10.3390/rs10121940.
Lindner, T., J. Puck, and A. Verbeke. 2022. “Beyond addressing multicollinearity: Robust quantitative analysis and machine learning in international business research.” J. Int. Bus. Stud. 53 (7): 1307–1314. https://doi.org/10.1057/s41267-022-00549-z.
Loh, W. Y. 2011. “Classification and regression trees.” Wiley Interdiscip. Rev.: Data Min. Knowl. Discovery 1 (1): 14–23.
Malyuta, D. A. 2015. “Analysis of factors affecting pavement markings and pavement marking retroreflectivity in Tennessee highways.” Ph.D. dissertation, Dept. of Civil Engineering, Univ. of Tennessee at Chattanooga.
Migletz, J., J. L. Graham, D. W. Harwood, and K. M. Bauer. 2001. “Service life of durable pavement markings.” Transp. Res. Rec. 1749 (1): 13–21. https://doi.org/10.3141/1749-03.
Mousa, M. R., and M. Hassan. 2021. Maintenance and restriping strategies for pavement markings on asphalt pavements in Louisiana. Baton Rouge, LA: LSU Scholarly Repository.
Mousa, M. R., M. Hassan, P. Carlson, J. Davis, and S. R. Mousa. 2021a. “Development of cost-effective restriping strategies using standard width and wide waterborne paints on asphalt pavements in hot and humid climates.” Transp. Res. Rec. 2675 (9): 284–295. https://doi.org/10.1177/03611981211001872.
Mousa, M. R., S. R. Mousa, M. Hassan, P. Carlson, and I. A. Elnaml. 2021b. “Predicting the retroreflectivity degradation of waterborne paint pavement markings using advanced machine learning techniques.” Transp. Res. Rec. 2675 (9): 483–494. https://doi.org/10.1177/03611981211002844.
Mousa, S. R., P. R. Bakhit, and S. Ishak. 2019. “An extreme gradient boosting method for identifying the factors contributing to crash/near-crash events: A naturalistic driving study.” Can. J. Civ. Eng. 46 (8): 712–721. https://doi.org/10.1139/cjce-2018-0117.
Mull, D. M., and W. E. Sitzabee. 2012. “Paint pavement marking performance prediction model.” J. Transp. Eng. 138 (5): 618–624. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000360.
Müller, A. C., and S. Guido. 2016. Introduction to machine learning with python: A guide for data scientists. Sebastopol, CA: O’Reilly Media.
Nabipour, N., N. Karballaeezadeh, A. Dineva, A. Mosavi, S. D. Mohammadzadeh, and S. Shamshirband. 2019. “Comparative analysis of machine learning models for prediction of remaining service life of flexible pavement.” Mathematics 7 (12): 1198. https://doi.org/10.3390/math7121198.
Ozelim, L., and R. E. Turochy. 2014. “Modeling retroreflectivity performance of thermoplastic pavement markings in Alabama.” J. Transp. Eng. 140 (6): 05014001. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000661.
Pedregosa, F., et al. 2011. “Scikit-learn: Machine learning in python.” J. Mach. Learn. Res. 12 (Nov): 2825–2830.
Pike, A. M., and P. Songchitruksa. 2015. “Predicting pavement marking service life with transverse test deck data.” Transp. Res. Rec. 2482 (1): 16–22. https://doi.org/10.3141/2482-03.
Probst, P., M. N. Wright, and A. L. Boulesteix. 2019. “Hyperparameters and tuning strategies for random forest.” Wiley Interdiscip. Rev.: Data Min. Knowl. Discovery 9 (3): e1301.
Robertson, J., W. Sarasua, J. Johnson, and W. Davis. 2013. “A methodology for estimating and comparing the lifecycles of high-build and conventional waterborne pavement markings on primary and secondary roads in South Carolina.” Public Works Manage. Policy 18 (4): 360–378. https://doi.org/10.1177/1087724X12451441.
Ronaghan, S. 2018. “The mathematics of decision trees, random forest and feature importance in scikit-learn and spark.” Towards Data Science. Accessed July 27, 2022. https://towardsdatascience.com/the-mathematics-of-decision-trees-random-forest-and-feature-importance-in-scikit-learn-and-spark-f2861df67e3/.
Sadler, J. M., J. L. Goodall, M. M. Morsy, and K. Spencer. 2018. “Modeling urban coastal flood severity from crowd-sourced flood reports using Poisson regression and random forest.” J. Hydrol. 559 (Apr): 43–55. https://doi.org/10.1016/j.jhydrol.2018.01.044.
Sasidharan, L., V. Karwa, and E. T. Donnell. 2009. “Use of pavement marking degradation models to develop a pavement marking management system.” Public Works Manage. Policy 14 (2): 148–173. https://doi.org/10.1177/1087724X09349513.
Shoaib, M. M., and M. Y. Abu-Farsakh. 2024. “Exploring tree-based machine learning models to estimate the ultimate pile capacity from cone penetration test data.” Transp. Res. Rec. 2678 (1): 136–149. https://doi.org/10.1177/03611981231170128.
Sitzabee, W. E., J. E. Hummer, and W. Rasdorf. 2009. “Pavement marking degradation modeling and analysis.” J. Infrastruct. Syst. 15 (3): 190–199. https://doi.org/10.1061/(ASCE)1076-0342(2009)15:3(190).
Sitzabee, W. E., E. D. White, and A. W. Dowling. 2013. “Degradation modeling of polyurea pavement markings.” Public Works Manage. Policy 18 (2): 185–199. https://doi.org/10.1177/1087724X12462831.
Smadi, O., R. R. Souleyrette, D. J. Ormand, and N. Hawkins. 2008. “Pavement marking retroreflectivity: Analysis of safety effectiveness.” Transp. Res. Rec. 2056 (1): 17–24. https://doi.org/10.3141/2056-03.
Sun, H., D. Gui, B. Yan, Y. Liu, W. Liao, Y. Zhu, C. Lu, and N. Zhao. 2016. “Assessing the potential of random forest method for estimating solar radiation using air pollution index.” Energy Convers. Manage. 119 (Jul): 121–129. https://doi.org/10.1016/j.enconman.2016.04.051.
Thamizharasan, A., W. A. Sarasua, D. A. Clarke, and W. J. Davis. 2003. “A methodology for estimating the lifecycle of interstate highway pavement marking retroreflectivity.” In Proc., 82nd Annual Meeting of the Transportation Research Board of the National Academies. Washington, DC: Transportation Research Board.
Thomas, G. B., and C. Schloz. 2001. Durable, cost-effective pavement markings phase I: Synthesis of current research. Ames, IA: Iowa State Univ., Center for Transportation Research and Education.
Triscowati, D. W., B. Sartono, A. Kurnia, D. Dirgahayu, and A. W. Wijayanto. 2020. “Classification of rice-plant growth phase using supervised random forest method based on landsat-8 multitemporal data.” Int. J. Remote Sens. Earth Sci. (IJReSES) 16 (2): 187–196. https://doi.org/10.30536/j.ijreses.2019.v16.a3217.
UÇAR, M. K. 2019. “Eta correlation coefficient based feature selection algorithm for machine learning: E-Score feature selection algorithm.” J. Intell. Syst.: Theory Appl. 2 (1): 7–12.
Umali, J., and E. Barrios. 2014. “Nonparametric principal components regression.” Commun. Stat.-Simul. Comput. 43 (7): 1797–1810. https://doi.org/10.1080/03610918.2012.744046.
Wang, C., Z. Wang, and Y. C. Tsai. 2016. “Piecewise multiple linear models for pavement marking retroreflectivity prediction under effect of winter weather events.” Transp. Res. Rec. 2551 (1): 52–61. https://doi.org/10.3141/2551-07.
Wang, S. 2010. “Comparative analysis of NTPEP pavement marking performance evaluation results.” Masters’ thesis, Dept. of Civil Engineering, Univ. of Akron.
Wu, X., J. He, T. Yip, and N. Lu. 2016. “A two-stage random forest method for short-term load forecasting.” In Proc., 2016 IEEE Power and Energy Society General Meeting (PESGM), 1–5. New York: IEEE.
Yadav, D. 2019. “Categorical encoding using label-encoding and one-hot-encoder.” Towards Data Science. Accessed July 15, 2022. https://towardsdatascience.com/categorical-encoding-using-label-encoding-and-one-hot-encoder-911ef77fb5bd/.
Yang, G., W. Yu, K. Wang, Y. Peng, Q. J. Li, and A. Zhang. 2021. “Random forest–based pavement surface friction prediction using high-resolution 3D image data.” J. Test. Eval. 49 (2): 1141–1152.
Yang, L., and A. Shami. 2020. “On hyperparameter optimization of machine learning algorithms: Theory and practice.” Neurocomputing 415 (Nov): 295–316. https://doi.org/10.1016/j.neucom.2020.07.061.
Yoon, J. 2021. “Forecasting of real GDP growth using machine learning models: Gradient boosting and random forest approach.” Comput. Econ. 57 (1): 247–265. https://doi.org/10.1007/s10614-020-10054-w.
Zhang, S., Z. Tan, J. Liu, Z. Xu, and Z. Du. 2020. “Determination of the food dye indigotine in cream by near-infrared spectroscopy technology combined with random forest model.” Spectrochim. Acta, Part A 227 (Feb): 117551. https://doi.org/10.1016/j.saa.2019.117551.
Zhang, Y., and D. Wu. 2006. “Methodologies to predict service lives of pavement marking materials.” J. Transp. Res. Forum 45 (3): 5–18.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part B: Pavements
Volume 150 • Issue 2 • June 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Jan 27, 2023
Accepted: Dec 29, 2023
Published online: Mar 11, 2024
Published in print: Jun 1, 2024
Discussion open until: Aug 11, 2024
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.