Detection of Unreported Treatments in Pavement Management System of Iowa DOT Using Machine Learning Classification Algorithm
Publication: Journal of Transportation Engineering, Part B: Pavements
Volume 148, Issue 4
Abstract
Treatment records are among the most frequently underreported data items in pavement management systems (PMSs), which negatively affects various PMS analysis tools, such as pavement performance and deterioration models. Disregarding unreported treatments may lead to inaccurate pavement age and condition estimates, resulting in erroneous and nonoptimal maintenance and rehabilitation decisions. Nevertheless, the unreported and frequently missing pavement treatment data has received limited attention. Hence, this paper contributes to the body of knowledge by introducing a methodology for detecting unreported treatment actions and their occurrence probabilities over pavement age using a machine learning classification algorithm. Logistic regression models were developed using historical pavement condition data and validated on two levels: (1) split validation; and (2) manual validation using video logs of the pavement condition before and after treatment application. The results show that the developed models can detect unreported pavement treatments with accuracy, precision, and F1 scores ranging from 89% to 96%, 82% to 91%, and 70% to 85%, respectively. The presented methodology and developed models will help highway agencies identify unreported and missing pavement treatments, contributing to more cost-effective maintenance and rehabilitation decisions.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request. The list of available models, codes, and data is listed below:
•
The code of the machine learning classification algorithm is available upon request.
•
The PMIS data is available online on the Iowa DOT open data website.
References
Abra, Ens. 2012. Development of a flexible framework for deterioration modelling in infrastructure asset management. Toronto: Univ. of Toronto.
Abukhalil, Y., and O. Smadi. 2022a. “A bootstrap-based integer programming algorithm for budget allocation in pavement management systems.” J. Infrastruct. Syst. 28 (1): 04021056. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000663.
Abukhalil, Y., and O. Smadi. 2022b. “Cart algorithm: A data-driven approach to automate maintenance selection in pavement management systems.” J. Infrastruct. Syst. 28 (3): 04022019. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000693.
Alcázar, E., R. Hassan, and K. McManus. 2004. “Towards sustainable local urban road pavements.” WIT Trans. Ecol. Environ. 72 (12): 663–671.
Amin, S. R., and L. E. Amador-Jiménez. 2017. “Backpropagation neural network to estimate pavement performance: Dealing with measurement errors.” Road Mater. Pavement Des. 18 (5): 1218. https://doi.org/10.1080/14680629.2016.1202129.
Beckley, M. E. 2016. Pavement deterioration modeling using historical roughness data. Tempe, AZ: Arizona State Univ.
Chen, C.-T., C.-T. Hung, J.-D. Lin, and P.-H. Sung. 2015. “Application of a decision tree method with a spatiotemporal object database for pavement maintenance and management.” J. Mar. Sci. Technol. 23 (3): 302–307. https://doi.org/10.6119/JMST-014-0327-5.
Chi, S., J. Hwang, M. Arellano, Z. Zhang, and M. Murphy. 2013. “Development of network-level project screening methods supporting the 4-year pavement management plan in Texas.” J. Manage. Eng. 29 (4): 482–494. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000158.
Clarke, B., E. Fokoué, and H. H. Zhang. 2009. Spline smoothing BT—Principles and theory for data mining and machine learning, 117–170. New York: Springer.
Evans, L. D., and A. Eltahan. 2000. LTPP profile variability. Columbia, MD: ERES Consultants, Inc.
France-Mensah, J., and W. J. O’Brien. 2018. “Budget allocation models for pavement maintenance and rehabilitation: Comparative case study.” J. Manage. Eng. 34 (2): 5018002. https://doi.org/10.1061/(ASCE)ME.1943-5479.0000599.
Gao, L., S. Qiu, and T. R. Prasad. 2017. “Bayesian detection of unrecorded maintenance and rehabilitation treatments in pavement management.” In Proc., Transportation Research Board 96th Annual Meeting. Washington, DC: Transportation Research Board.
Gao, L., Y. Yu, Y. Hao Ren, and P. Lu. 2021. “Detection of pavement maintenance treatments using deep-learning network.” In Journal of transportation research board, 1–10. Los Angeles: SAGE.
Greene, W. H. 2011. LIMDEP version 9 student reference guide. New York: Econometric Software, Inc.
Guo, F., O. Swei, J. Gregory, and R. Kirchain. 2018. “Sensitivity analysis of performance metrics to different parameters in pavement management system.” In Proc., Transportation Research Board 97th Annual Meeting. Washington, DC: Transportation Research Board.
Hafez, M., K. Ksaibati, and R. Atadero. 2018. Comprehensive evaluation of pavement maintenance activities applied to Colorado low-volume paved roads-phase II. Denver: Colorado Department of Transportation.
Harvey, J., J. Roesler, J. Farver, and L. Liang. 2000. Preliminary evaluation of proposed LLPRS rigid pavement structures and design inputs. Berkeley, CA: Pavement Research Center, Institute of Transportation Studies, Univ. of California at Berkeley.
Hosseini, S. A. 2020. Data-driven framework for modeling deterioration of pavements in the state of Iowa. Ames, IA: Iowa State Univ.
Irrgang, F. C., and T. H. Maze. 1993. Status of pavement management systems and data analysis models at state highway agencies. Washington, DC: Transportation Research Record.
Kulkarni, R. B., and R. W. Miller. 2003. “Pavement management systems: Past, present, and future.” Transp. Res. Rec. 1853 (1): 65–71. https://doi.org/10.3141/1853-08.
Manty, A., and T. Colling. 2018. Analysis of TAMC investment reporting data for network level modeling on the locally owned road system in Michigan. Houghton, MI: Center for Technology & Training, Michigan Technological Univ.
Ozbay, K., and R. Laub. 2001. Models for pavement deterioration using LTPP. Piscataway, NJ: LTPP.
Pérez-Acebo, H., S. Bejan, and H. Gonzalo-Orden. 2018. “Transition probability matrices for flexible pavement deterioration models with half-year cycle time.” Int. J. Civ. Eng. 16 (9): 1045–1056. https://doi.org/10.1007/s40999-017-0254-z.
Pérez-Acebo, H., N. Mindra, A. Railean, and E. Rojí. 2019. “Rigid pavement performance models by means of Markov Chains with half-year step time.” Int. J. Pavement Eng. 20 (7): 830–843. https://doi.org/10.1080/10298436.2017.1353390.
Plati, C., P. Georgiou, and V. Papavasiliou. 2016. “Simulating pavement structural condition using artificial neural networks.” Struct. Infrastruct. Eng. 12 (9): 1127–1136. https://doi.org/10.1080/15732479.2015.1086384.
Pour, S. A., and D. H. S. Jeong. 2012. “Realistic life-cycle cost analysis with typical sequential patterns of pavement treatment through association analysis.” Transp. Res. Rec. 2304 (1): 104–111. https://doi.org/10.3141/2304-12.
Pulugurta, H. 2007. Development of pavement condition forecasting models. Toledo, OH: Univ. of Toledo.
Safaei, N., O. Smadi, A. Masoud, and B. Safaei. 2021. “An automatic image processing algorithm based on crack pixel density for pavement crack detection and classification.” Int. J. Pavement Res. Technol. 2021 (Jan): 1–14. https://doi.org/10.1007/s42947-021-00006-4.
Saha, P., K. Ksaibati, and R. Atadero. 2017. “Developing pavement distress deterioration models for pavement management system using Markovian probabilistic process.” Adv. Civ. Eng. 2017 (1): 1–9. https://doi.org/10.1155/2017/8292056.
Shahin, M. Y., and J. A. Walther. 1990. Pavement maintenance management for roads and streets using the PAVER system. Champaign, IL: PAVER.
Tasmin, T. 2020. Developing a relationship between subjective and objective pavement condition data. Melbourne, VIC, Australia: Swinburne University of Science and Technology.
Thomas, O., and J. Sobanjo. 2013. “Comparison of Markov chain and semi-Markov models for crack deterioration on flexible pavements.” J. Infrastruct. Syst. 19 (2): 186–195. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000112.
Wang, K. C. P., J. Zaniewski, and G. Way. 1994. “Probabilistic behavior of pavements.” J. Transp. Eng. 120 (3): 358–375. https://doi.org/10.1061/(ASCE)0733-947X(1994)120:3(358).
Washington, S. P., M. G. Karlaftis, and F. L. Mannering. 2004. “Statistical and econometric methods for transportation data analysis.” Marit. Econ. Logist. 6 (45): 187–189. https://doi.org/10.1201/9780429244018.
Yamany, M. S. 2020. “Stochastic performance and maintenance optimization models for pavement infrastructure management.” Ph.D. dissertation, Lyles School of Civil Engineering, Purdue Univ.
Yamany, M. S., and D. M. Abraham. 2021. “Hybrid approach to incorporate preventive maintenance effectiveness into probabilistic pavement performance models.” J. Transp. Eng. Part B: Pavements 147 (1): 4020077. https://doi.org/10.1061/JPEODX.0000227.
Yamany, M. S., and E. Elwakil. 2020. “Modelling of cast-in-place concrete tunnel liners condition.” Struct. Infrastruct. Eng. 16 (8): 1147–1160. https://doi.org/10.1080/15732479.2019.1687529.
Yamany, M. S., T. U. Saeed, M. Volovski, and A. Ahmed. 2020. “Characterizing the performance of interstate flexible pavements using artificial neural networks and random parameters regression.” J. Infrastruct. Syst. 26 (2): 4020010. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000542.
Yoo, H.-S., and Y.-S. Kim. 2016. “Development of a crack recognition algorithm from non-routed pavement images using artificial neural network and binary logistic regression.” KSCE J. Civ. Eng. 20 (4): 1151–1162. https://doi.org/10.1007/s12205-015-1645-9.
Zhou, G., L. Wang, D. Wang, and S. Reichle. 2010. “Integration of GIS and data mining technology to enhance the pavement management decision making.” J. Transp. Eng. 136 (4): 332–341. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000092.
Ziari, H., J. Sobhani, J. Ayoubinejad, and T. Hartmann. 2016. “Prediction of IRI in short and long terms for flexible pavements: ANN and GMDH methods.” Int. J. Pavement Eng. 17 (9): 776–788. https://doi.org/10.1080/10298436.2015.1019498.
Zimmerman, K. A. 2017. Pavement management systems: Putting data to work. Washington, DC: National Cooperative Highway Research Program.
Information & Authors
Information
Published In
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Jun 13, 2021
Accepted: May 24, 2022
Published online: Sep 28, 2022
Published in print: Dec 1, 2022
Discussion open until: Feb 28, 2023
ASCE Technical Topics:
- Algorithms
- Architectural engineering
- Artificial intelligence and machine learning
- Building management
- Computer programming
- Computing in civil engineering
- Data analysis
- Engineering fundamentals
- Gravels
- Infrastructure
- Maintenance and operation
- Mathematics
- Methodology (by type)
- Pavement condition
- Pavements
- Research methods (by type)
- Systems engineering
- Systems management
- Transportation engineering
- Validation
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.
Cited by
- Qingwei Zeng, Feng Xiao, Hui Zhang, Shunxin Yang, Qixuan Cui, Data Cleaning Framework for Pavement Maintenance and Rehabilitation Decision-Making in Pavement Management System Based on Artificial Neural Networks, Journal of Infrastructure Systems, 10.1061/JITSE4.ISENG-2479, 30, 3, (2024).