 |
[email protected] |
 |
3275638434 |
 |
 |
| Paper Publishing WeChat |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Development of Machine Learning Based Prediction Models to Prioritize the Sewer Inspections
Madhuri Arjun1 and Arjun Nanjundappa2
Full-Text PDF
XML 180 Views
DOI:10.17265/1934-7359/2025.03.001
1. Department of Civil Engineering, University of Texas at Arlington, 1221 West Mitchell Street, Room # 313, Arlington, TX 76013, USA
2. Mavenir Systems, 1700 International Pkwy, Richardson, TX 75082, USA
Sewer pipe condition assessment by performing regular inspections is crucial for ensuring the systems’ effective operation and maintenance. CCTV (closed-circuit television) is widely employed in North America to examine the internal conditions of sewage pipes. Due to the extensive inventory of pipes and associated costs, it is not practical for municipalities to conduct inspections on each sanitary sewage pipe section. According to the ASCE (American Society of Civil Engineers) infrastructure report published in 2021, combined investment needs for water and wastewater systems are estimated to be $150 billion during 2016-2025. Therefore, new solutions are needed to fill the trillion-dollar investment gap to improve the existing water and wastewater infrastructure for the coming years. ML (machine learning) based prediction model development is an effective method for predicting the condition of sewer pipes. In this research, sewer pipe inspection data from several municipalities are collected, which include variables such as pipe material, age, diameter, length, soil type, slope of construction, and PACP (Pipeline Assessment Certification Program) score. These sewer pipe data exhibit a severe imbalance in pipes’ PACP scores, which is considered the target variable in the development of models. Due to this imbalanced dataset, the performance of the sewer prediction model is poor. This paper, therefore, aims to employ oversampling and hyperparameter tuning techniques to treat the imbalanced data and improve the model’s performance significantly. Utility owners and municipal asset managers can utilize the developed models to make more informed decisions on future inspections of sewer pipelines.
Sanitary sewers, asset management, pipe inspection, ML algorithms, condition prediction models.
Journal of Civil Engineering and Architecture 19 (2025) 105-119
doi: 10.17265/1934-7359/2025.03.001
[1] Najafi, M., and Gokhale, S. B. 2022. Trenchless Technology: Pipeline and Utility Design, Construction, and Renewal. New York: McGraw-Hill.
[2] Arjun, M. S., Rahman, S., Nanjundappa, A., and Hammouri, A. P. 2024. “Adapting Oversampling and Hyperparameters Tuning to Improve the Performance of Prediction Model for Sewers.” In Proceedings of the ASCE Pipeline Conference, July 27-31, 2024, Calgary, Alberta, Canada.
[3] EPA. 2007. “Innovation and Research for Water Infrastructure for the 21st Century.” www.Ep.gov/nrmrl.
[4] EPA. 2009. “Condition Assessment of Wastewater Collection Systems.” www.Ep.gov/nrmrl.
[5] ASCE. 2021. Report Card for America’s Infrastructure. New York: American Society of Civil Engineers (ASCE).
[6] American Water Works Association (AWWA). 2012. “Buried No Longer: Confronting America’s Water Infrastructure Challenge.” https://www.awwa.org/Portals/
0/files/legreg/documents/BuriedNoLonger.pdf.
[7] Atambo, D., Rahman, S., Arjun, M., Kaushal, V., Tehrani, A., and Najafi, M. 2023. “Factors Influencing Watermain Break Rates.” In Proceedings of the ASCE Pipeline Conference, August 12-16, 2023, San Antonio, TX, U.S.
[8] Rahman, S., Arjun, M., Atambo, D., Hassi, S., and Jibreen, A. 2023. “Municipal Pipe Material Joints: Design and Sealing.” In Proceedings of the ASCE Pipeline Conference, August 12-16, 2023, San Antonio, TX, U.S.
[9] EPA. 2015. “Condition Assessment of Underground Pipes.” www.Ep.gov/nrmrl.
[10] Arjun, M., Kaushal, V., Shirkhanloo, S., Rahman, S., and Najafi, M. 2023. “A Review of Rehabilitation Methods for Aging Pipe Culverts by Spray Applied Pipe Lining, Grouting, and Sliplining.” In Proceedings of the ASCE Pipeline Conference, August 12-16, 2023, San Antonio, TX, U.S.
[11] Geisbush, J., Collins, C., and Arjun, M. P. 2024. “Developing and Executing Large Diameter Water Pipeline Physical Entry Inspection Protocols.” In Proceedings of the ASCE Pipeline Conference, July 27-31, 2024, Calgary, Alberta, Canada.
[12] Opila, M. C. 2011. “Structural Condition Scoring of Buried Sewer Pipes for Risk-Based Decision Making.” Ph.D. thesis, University of Delaware.
[13] National Association of Sewer Service Companies (NASSCO), Pipeline Assessment Certification Manual, Dallas (2015).
[14] Shirkhanloo, S., Arjun, M., Najafi, M., Kaushal, V., Kaur, K., and Jibreen, A. 2023. “Investigation of KNN and Decision Tree Methods’ Efficiency in Developing Prediction Models for Sewer Pipes.” In Proceedings of the ASCE Pipeline Conference, August 12-16, 2023, San Antonio, TX, U.S.
[15] Najafi, M., and Kulandaivel, G. 2005. “Pipeline Condition Prediction Using Neural Network Models.” Pipelines 2005.
[16] Chughtai, F. R. M. 2008. “Integrated condition assessment models for sustainable sewer pipelines.” thesis
[17] Mashford, J., Marlow, D., Tran, D., and May, R. (2011). “Prediction of Sewer Condition Grade Using Support Vector Machines.” Journal of Computing in Civil Engineering, 25(4), 283–290.
[18] Sousa, V., Matos, J. P., and Matias, N. 2014. “Evaluation of artificial intelligence tool performance and uncertainty for predicting sewer structural condition.” Automation in Construction, 44, 84–91.
[19] Kabir, G., Balek, N. B. C., and Tesfamariam, S. 2018. “Sewer Structural Condition Prediction Integrating Bayesian Model Averaging with Logistic Regression.” Journal of Performance of Constructed Facilities, 32(3), 04018019.
[20] Arjun, M. 2023. “Comparison of Condition Prediction Models to Prioritize Sewer Pipe Inspections.” Ph.D. thesis, University of Texas at Arlington.
[21] Ariaratnam, S. T., El-Assaly, A., and Yang, Y. 2001. “Assessment of Infrastructure Inspection Needs Using Logistic Models.” Journal of Infrastructure Systems, 7(4), 160–165.
[22] Tran, D., Ng, A., and Perera, B. (2006). “Neural networks deterioration models for serviceability condition of buried stormwater pipes.” Engineering Applications of Artificial Intelligence, 20(8), 1144–1151.
[23] Tran, H. D. 2007. “Investigation of Deterioration Models for Stormwater Pipe Systems.” Doctoral Dissertation. Victoria University. Melbourne, Australia.
[24] Chughtai, F., and Zayed, T. 2008. “Integrating WRc and CERIU Condition Assessment Models and Classification Protocols for Sewer Pipelines.” Journal of Infrastructure Systems, 17(3), 129–136
[25] Tran, D. H., Perera, B. J. C., and Ng, A. 2009. “Comparison of Structural Deterioration Models for Stormwater Drainage Pipes.” Computer-Aided Civil and Infrastructure Engineering, 24(2), 145–156.
[26] Khan, Z., Zayed, T., and Moselhi, O. 2010. “Structural Condition Assessment of Sewer Pipelines.” Journal of Performance of Constructed Facilities, 24(2), 170–179.
[27] Lubini, A. T., and Fuamba, M. 2011. “Modeling of the deterioration timeline of sewer systems.” NRC Research Press.
[28] Mashford, J., Marlow, D., Tran, D., and May, R. 2011. “Prediction of Sewer Condition Grade Using Support Vector Machines.” Journal of Computing in Civil Engineering, 25(4), 283–290.
[29] Salman, B., and Salem, O. (2012). “Modeling Failure of Wastewater Collection Lines Using Various Section-Level Regression Models.” Journal of Infrastructure Systems, 18(2), 146–154.
[30] Syachrani, S., Jeong, H. S. “D., and Chung, C. S. 2013. “Decision Tree–Based Deterioration Model for Buried Wastewater Pipelines.” Journal of Performance of Constructed Facilities, 27(5), 633–645.
[31] Harvey, R. R., and Mcbean, E. A. (2014). “Predicting the structural condition of individual sanitary sewer pipes with random forests.” Canadian Journal of Civil Engineering, 41(4), 294–303.
[32] Bakry, I., Alzraiee, H., Kaddoura, K., Masry, M. E., and Zayed, T. (2016). “Condition Prediction for Chemical Grouting Rehabilitation of Sewer Networks.” Journal of Performance of Constructed Facilities, 30(6), 04016042.
[33] Gedam, A., Mangulkar, S., and Gandhi, B. 2016. Prediction of sewer pipe main condition using the linear regression approach. Journal of Geoscience and Environment Protection, 100-105.
[34] Hernandez, N., Caradot, N., Sonnenberg, H., Rouault, P., and Torres, A. 2017. Support Tools to Predict the Critical Structural Condition of Uninspected Sewer Pipes in Bogota D.C. The Leading Edge Sustainable Asset Management of Water and Wastewater Infrastructure Conference.
Trondheim, Norway.
[35] Laakso, T., Kokkonen, T., Mellin, I., and Vahala, R. 2018. Sewer Condition Prediction and Analysis of Explanatory Factors. Water, 1239.
[36] Malek Mohammadi, M. 2019. “Development of Condition Prediction Models for Sanitary Sewer Pipes.” Ph.D. thesis, University of Texas at Arlington.
[37] Laakso, T., Kokkonen, T., Mellin, I., and Vahala, R. 2018. Sewer Condition Prediction and Analysis of Explanatory Factors. Water, 1239.
[38] Loganathan, K. 2021. Development of a Model to Prioritize Inspection and Condition Assessment of Gravity Sanitary Sewer Systems (Doctoral dissertation, The University of Texas at Arlington).
[39] Shirkhanloo. S. 2022. Evaluation of Decision-Making Prediction Models for Sewer Pipes Asset Management (Doctoral dissertation, The University of Texas at Arlington).
[40] Müller, A. C., and Guido, S. 2016. Introduction to Machine Learning with Python: A Guide for Data Scientists. Boston: O’Reilly.
[41] Salman, B. 2010. “Infrastructure Management and Deterioration Risk Assessment of Wastewater Collection Systems.” Ph.D. thesis, University of Cincinnati.
[42] Teh, K., Armitage, P., Tesfaye, S., Selvarajah, D., and Wilkinson, I. D. 2020. “Imbalanced Learning: Improving Classification of Diabetic Neuropathy from Magnetic Resonance Imaging.” PLoS One 15 (12): e0243907.
[43] Hosmer, D. W., Lemeshow, S., and Sturdivant, R. X. 2013. Applied Logistic Regression. Hoboken, NJ: Wiley.
[44] Hossin, M., and Sulaiman, M. 2015. “A Review on Evaluation Metrics for Data Classification Evaluations.” International Journal of Data Mining and Knowledge Management Process 5: 1-11.