Pavement Safety Characteristics Evaluation Utilizing Crowdsourced Vehicular and Cellular Sensor Data
Publication: Journal of Transportation Engineering, Part B: Pavements
Volume 150, Issue 3
Abstract
Monitoring pavement conditions using crowdsourced vehicular data can significantly contribute to real-time and cost-effective pavement maintenance decision-making. This paper presents the development of various machine learning models for predicting crucial pavement characteristics essential for ensuring roadway safety, including roadway longitudinal grade, cross slope, international roughness index, surface rutting, and pavement skid resistance. The study collected vehicular sensing data and paired it with field pavement characteristics obtained using innovative instruments on selected asphalt and concrete sections in Oklahoma. Seven machine learning models were trained using the AutoGluon platform, yielding highly accurate predictions for safety-related roadway characteristics. The weighted ensemble L2, random forest, and category boosting (CatBoost) models exhibited the highest accuracy, with R-squared values exceeding 0.9, while the k-nearest neighbor algorithm and LightGBM models showed lower competitiveness. The inference latency of the models varied, with CatBoost demonstrating the lowest latency and weighted ensemble L2 achieving the highest accuracy at the expense of slightly higher inference latency. The choice of model depends on the specific application, whether it be pavement network management or real-time roadway condition monitoring. The findings from this research empower transportation agencies to efficiently screen the pavement network for further inspection or maintenance, thus enhancing transportation safety by providing instant alerts to drivers about potential high-risk pavement sections, resulting in safer and more reliable transportation infrastructure.
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 codes that support the findings of this study are available from the corresponding author upon reasonable request.
References
Aagesen, H. W., V. Heikinheimo, and H. Tenkanen. 2022. “Nearest neighbor analysis with large datasets.” Accessed September 16, 2022. https://autogis-site.readthedocs.io/en/latest/notebooks/L3/06_nearest-neighbor-faster.html.
AASHTO. 2010. Highway safety manual. Washington, DC: AASHTO.
Abdishakur. 2019. “Nearest neighbour analysis with geospatial data.” Accessed September 16, 2022. https://towardsdatascience.com/nearest-neighbour-analysis-with-geospatial-data-7bcd95f34c0e.
Al Daoud, E. 2019. “Comparison between XGBoost, LightGBM and CatBoost using a home credit dataset.” Int. J. Comput. Inf. Eng. 13 (1): 6–10.
Alessandroni, G., et al. 2014. “SmartRoadSense: Collaborative road surface condition monitoring.” In Proc., 8th UBICOMM, 210–215. Rome: International Academy, Research, and Industry Association. https://doi.org/10.13140/RG.2.1.3124.2726.
ASTM. 2021a. Standard practice for computing international roughness index of roads from longitudinal profile measurements. ASTM E1926-08. West Conshohocken, PA: ASTM.
ASTM. 2021b. Standard test method for measuring the skid resistance of pavements and other trafficked surfaces using a continuous reading, fixed-slip technique. ASTM E2340M-11. West Conshohocken, PA: ASTM.
Babashamsi, P., N. I. M. Yusoff, H. Ceylan, N. G. M. Nor, and H. S. Jenatabadi. 2016. “Evaluation of pavement life cycle cost analysis: Review and analysis.” Int. J. Pavement Res. Technol. 9 (4): 241–254. https://doi.org/10.1016/j.ijprt.2016.08.004.
Cao, W., Q. Liu, and Z. He. 2020. “Review of pavement defect detection methods.” IEEE Access 8 (Jan): 14531–14544. https://doi.org/10.1109/ACCESS.2020.2966881.
Caruana, R., A. Niculescu-Mizil, G. Crew, and A. Ksikes. 2004. “Ensemble selection from libraries of models.” In Proc., 21st Int. Conf. on Machine Learning. New York: Association for Computing Machinery.
Cover, T., and P. Hart. 1967. “Nearest neighbor pattern classification.” IEEE Trans. Inf. Theory 13 (1): 21–27. https://doi.org/10.1109/TIT.1967.1053964.
Cui, L., Z. Qi, Z. Chen, F. Meng, and Y. Shi. 2015. “Pavement distress detection using random decision forests.” In Proc., Data Science: 2nd Int. Conf., ICDS 2015, Sydney, Australia, 95–102. Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-319-24474-7_14.
Davies, L., and U. Gather. 1993. “The identification of multiple outliers.” J. Am. Stat. Assoc. 88 (423): 782–792. https://doi.org/10.1080/01621459.1993.10476339.
Dennis, E. P., Q. Hong, R. Wallace, W. Tansil, and M. Smith. 2014. “Pavement condition monitoring with crowdsourced connected vehicle data.” Transp. Res. Rec. 2460 (1): 31–38. https://doi.org/10.3141/2460-04.
Eisenbach, M., R. Stricker, D. Seichter, K. Amende, K. Debes, M. Sesselmann, D. Ebersbach, U. Stoeckert, and H.-M. Gross. 2017. “How to get pavement distress detection ready for deep learning? A systematic approach.” In Proc., 2017 Int. Joint Conf. on Neural Networks (IJCNN), 2039–2047. New York: IEEE.
Erickson, N., J. Mueller, A. Shirkov, H. Zhang, P. Larroy, M. Li, and A. Smola. 2020. “Autogluon-tabular: Robust and accurate autonomy for structured data.” Preprint, submitted March 13, 2020. https://arxiv.org/abs/200306505.
Eriksson, J., L. Girod, B. Hull, R. Newton, S. Madden, and H. Balakrishnan. 2008. “The pothole patrol: Using a mobile sensor network for road surface monitoring.” In Proc., 6th Int. Conf. on Mobile Systems, Applications, and Services, 29–39. New York: Association for Computing Machinery. https://doi.org/10.1145/1378600.1378605.
Géron, A. 2019. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. Sebastopol, CA: O’Reilly Media.
Gillies, S. 2024. “The shapely user manual.” Accessed April 17, 2024. https://doi.org/10.1061/JPEODX.0000239.
Hall, J. W., K. L. Smith, L. Titus-Glover, J. C. Wambold, T. J. Yager, and Z. Rado. 2009. Guide for pavement friction. Washington, DC: The National Academies Press. https://doi.org/10.17226/23038.
He, S., O. Salem, and B. Salman. 2021. “Decision support framework for project-level pavement maintenance and rehabilitation through integrating life cycle cost analysis and life cycle assessment.” J. Transp. Eng. Part B. Pavements 147 (1): 04020083. https://doi.org/10.1061/JPEODX.0000239.
Ho, C.-H., M. Snyder, and D. Zhang. 2020. “Application of vehicle-based sensing technology in monitoring vibration response of pavement conditions.” J. Transp. Eng. Part B. Pavements 146 (3): 04020053. https://doi.org/10.1061/JPEODX.0000205.
Ho, T. K. 1995. “Random decision forests.” In Proc., 3rd Int. Conf. on Document Analysis and Recognition, 278–282. New York: IEEE.
Hutter, F., L. Kotthoff, and J. Vanschoren. 2019. Automated machine learning: Methods, systems, challenges. Cham, Switzerland: Springer.
Jordahl, K., et al. 2020. “GeoPandas: Python tools for geographic data.” Accessed June 26, 2024. https://Github. Com/Geopandas/Geopandas.
Kuhn, M., and K. Johnson. 2013. Applied predictive modeling. New York: Springer.
Kulkarni, N. N., S. Dabetwar, J. Benoit, T. Yu, and A. Sabato. 2022. “Comparative analysis of infrared thermography processing techniques for roadways’ sub-pavement voids detection.” NDT & E Int. 129 (Jul): 102652. https://doi.org/10.1016/j.ndteint.2022.102652.
Kyriakou, C., S. Christodoulou, and L. Dimitriou. 2019a. “Do vehicles sense pavement surface anomalies?” In Vol. 1 of Proc., EC3 Conf., 56–64. Crete, Greece: European Council on Computing in Construction. https://doi.org/10.35490/EC3.2019.159.
Kyriakou, C., S. E. Christodoulou, and L. Dimitriou. 2016. “Roadway pavement anomaly classification utilizing smartphones and artificial intelligence.” In Proc., 2016 18th Mediterranean Electrotechnical Conf., 1–6. New York: IEEE.
Kyriakou, C., S. E. Christodoulou, and L. Dimitriou. 2019b. “Smartphone-based pothole detection utilizing artificial neural networks.” J. Infrastruct. Syst. 25 (3): 04019019. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000489.
Lee, T., C. Chun, and S. Ryu. 2021. “Detection of road-surface anomalies using a smartphone camera and accelerometer.” Sensors 21 (2): 561. https://doi.org/10.3390/s21020561.
Li, J. Q., W. Liu, X. Yang, P. Lu, and K. C. P. Wang. 2022. “Statistical safety performance models considering pavement and roadway characteristics.” J. Adv. Transp. 2022 (1): e5871601. https://doi.org/10.1155/2022/5871601.
Liu, F., X. Jiang, and M. Zhang. 2022. “Global burden analysis and AutoGluon prediction of accidental carbon monoxide poisoning by Global Burden of Disease Study 2019.” Environ. Sci. Pollut. Res. 29 (5): 6911–6928. https://doi.org/10.1007/s11356-021-15895-y.
Liu, W., J. Qiang Li, W. Yu, and G. Yang. 2021. “Change-point detection approaches for pavement dynamic segmentation.” J. Transp. Eng. Part B. Pavements 147 (2): 04021004. https://doi.org/10.1061/JPEODX.0000259.
Lord, D., X. Qin, and S. R. Geedipally. 2021. Highway safety analytics and modeling. Cambridge, MA: Elsevier.
Mandal, V., A. R. Mussah, and Y. Adu-Gyamfi. 2020. “Deep learning frameworks for pavement distress classification: A comparative analysis.” In Proc., IEEE Int. Conf. on Big Data (Big Data), 5577–5583. New York: IEEE.
Mohamed, A., M. M. M. Fouad, E. Elhariri, N. El-Bendary, H. M. Zawbaa, M. Tahoun, and A. E. Hassanien. 2014. “RoadMonitor: An intelligent road surface condition monitoring system.” In Proc., Intelligent Systems’ 2014: Advances in Intelligent Systems and Computing, 377–387. Cham, Switzerland: Springer. https://doi.org/10.1007/978-3-319-11310-4_33.
Mohan, P., V. N. Padmanabhan, and R. Ramjee. 2008. “Nericell: Rich monitoring of road and traffic conditions using mobile smartphones.” In Proc., 6th ACM Conf. on Embedded Network Sensor Systems. New York: Association for Computing Machinery. https://doi.org/10.1145/1460412.1460444.
Mueller, J., X. Shi, and A. Smola. 2020. “Faster, simpler, more accurate: Practical automated machine learning with tabular, text, and image data.” In Proc., 26th ACM SIGKDD Int. Conf. on Knowledge Discovery & Data Mining, 3509–3510. New York: Association for Computing Machinery. https://doi.org/10.1145/3394486.3406706.
Myles, A. J., R. N. Feudale, Y. Liu, N. A. Woody, and S. D. Brown. 2004. “An introduction to decision tree modeling.” J. Chemom. 18 (6): 275–285. https://doi.org/10.1002/cem.873.
Pan, Y., Y. Shang, G. Liu, Y. Xie, C. Zhang, and Y. Zhao. 2021. “Cost-effectiveness evaluation of pavement maintenance treatments using multiple regression and life-cycle cost analysis.” Constr. Build. Mater. 292 (Jul): 123461. https://doi.org/10.1016/j.conbuildmat.2021.123461.
Pedregosa, F., et al. 2011. “Scikit-learn: Machine learning in Python.” J. Mach. Learn. Res. 12 (85): 2825–2830.
Piryonesi, S. M., and T. E. El-Diraby. 2020. “Role of data analytics in infrastructure asset management: Overcoming data size and quality problems.” J. Transp. Eng. Part B. Pavements 146 (2): 04020022. https://doi.org/10.1061/JPEODX.0000175.
Qi, W., C. Xu, and X. Xu. 2021. “AutoGluon: A revolutionary framework for landslide hazard analysis.” Nat. Hazard. Res. 1 (3): 103–108. https://doi.org/10.1016/j.nhres.2021.07.002.
Ravi, R., D. Bullock, and A. Habib. 2021. “Pavement distress and debris detection using a mobile mapping system with 2D profiler lidar.” Transp. Res. Rec. 2675 (9): 428–438. https://doi.org/10.1177/03611981211002529.
Sankaranarayanan, S., J. Balan, J. R. Walsh, Y. Wu, S. J. Minnich, A. L. Piazza, C. Osborne, G. R. Oliver, J. L. Lesko, and K. L. Bates. 2021. “COVID-19 mortality prediction from deep learning in a large multistate EHR and LIS dataset: Algorithm development and validation.” J. Med. Internet Res. 23 (9): e30157. https://doi.org/10.2196/30157.
Santos Maia, R., S. Lacerda Costa, F. J. Craveiro Cunto, and V. T. F. Castelo Branco. 2021. “Relating weather conditions, drivers’ behavior, and tire-pavement friction to the analysis of microscopic simulated vehicular conflicts.” J. Transp. Eng. Part B. Pavements 147 (3): 04021037. https://doi.org/10.1061/JPEODX.0000293.
Schapire, R. E. 2003. “The boosting approach to machine learning: An overview.” In Nonlinear estimation and classification, 149–171. New York: Springer.
Sholevar, N., A. Golroo, and S. R. Esfahani. 2022. “Machine learning techniques for pavement condition evaluation.” Autom. Constr. 136 (Apr): 104190. https://doi.org/10.1016/j.autcon.2022.104190.
Than, N. T., C. Zhuoyuan, Z. Anggraini, K. P. Ping, and C. K. Keong. 2023. “Analysis and visualization for pavement condition assessment using network-level survey data.” In Roads and airports pavement surface characteristics, 168–178. Boca Raton, FL: CRC Press.
Tian, B., Y. Yuan, and Z. Yang. 2020. “Pavement management utilizing mobile crowd sensing.” Adv. Civ. Eng. 2020 (1): 4192602. https://doi.org/10.1155/2020/4192602.
Torres-Machí, C., A. Chamorro, E. Pellicer, V. Yepes, and C. Videla. 2015. “Sustainable pavement management: Integrating economic, technical, and environmental aspects in decision making.” Transp. Res. Rec. 2523 (1): 56–63. https://doi.org/10.3141/2523-07.
Vaccaro, L., G. Sansonetti, and A. Micarelli. 2021. “An empirical review of automated machine learning.” Computers 10 (1): 11. https://doi.org/10.3390/computers10010011.
Vanitha, N., K. Radhika, M. Maheshwari, P. Suresh, and T. Meenakshi. 2021. “IoT-based intelligent transportation system for safety.” In Cloud and IoT-based vehicular ad hoc networks, 47–65. Beverly, MA: Scrivener Publishing LLC.
Wang, K. C. P., Q. J. Li, G. Yang, Y. Zhan, and Y. Qiu. 2015. “Network level pavement evaluation with 1 mm 3D survey system.” J. Traffic Transp. Eng. 2 (6): 391–398. https://doi.org/10.1016/j.jtte.2015.10.005.
Wang, S., S. Zhao, and I. L. Al-Qadi. 2018. “Continuous real-time monitoring of flexible pavement layer density and thickness using ground penetrating radar.” NDT & E Int. 100 (Dec): 48–54. https://doi.org/10.1016/j.ndteint.2018.08.005.
Wong, K. J. 2022. “CatBoost vs. LightGBM vs. XGBoost.” Accessed October 18, 2022. https://towardsdatascience.com/catboost-vs-lightgbm-vs-xgboost-c80f40662924.
Yang, D., H. R. Karimi, and M. R. M. Aliha. 2021. “Comparison of testing method effects on cracking resistance of asphalt concrete mixtures.” Appl. Sci. 11 (11): 5094. https://doi.org/10.3390/app11115094.
Yoo, J., T. Joseph, D. Yung, S. A. Nasseri, and F. Wood. 2020. “Ensemble squared: A meta autonomy system.” Preprint, submitted December 10, 2020. https://arxiv.org/abs/201205390.
Yu, M., Z. You, G. Wu, L. Kong, C. Liu, and J. Gao. 2020. “Measurement and modeling of skid resistance of asphalt pavement: A review.” Constr. Build. Mater. 260 (Nov): 119878. https://doi.org/10.1016/j.conbuildmat.2020.119878.
Zhang, A., K. C. Wang, Y. Fei, Y. Liu, S. Tao, C. Chen, J. Q. Li, and B. Li. 2018. “Deep learning-based fully automated pavement crack detection on 3D asphalt surfaces with an improved CrackNet.” J. Comput. Civ. Eng. 32 (5): 04018041. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000775.
Zhang, A., K. C. Wang, B. Li, E. Yang, X. Dai, Y. Peng, Y. Fei, Y. Liu, J. Q. Li, and C. Chen. 2017. “Automated pixel-level pavement crack detection on 3D asphalt surfaces using a deep-learning network.” Comput.-Aided Civ. Infrastruct. Eng. 32 (10): 805–819. https://doi.org/10.1111/mice.12297.
Zhang, Z., X. Wang, and W. Zhu. 2021. “Automated machine learning on graphs: A survey.” Preprint, submitted March 1, 2021. https://arxiv.org/abs/210300742.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part B: Pavements
Volume 150 • Issue 3 • September 2024
Copyright
© 2024 American Society of Civil Engineers.
History
Received: Aug 3, 2023
Accepted: Apr 23, 2024
Published online: Jul 12, 2024
Published in print: Sep 1, 2024
Discussion open until: Dec 12, 2024
ASCE Technical Topics:
- Business management
- Engineering fundamentals
- Gravels
- Highway transportation
- Infrastructure
- Model accuracy
- Models (by type)
- Pavement condition
- Pavement rutting
- Pavement surface roughness
- Pavements
- Practice and Profession
- Public administration
- Public health and safety
- Safety
- Traffic engineering
- Traffic management
- Traffic safety
- Transportation engineering
- Vehicles
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.