A comparative study of statistical and machine learning methods to infer causes of pipe breaks in water supply networks

References

• Achim, D., F. Ghotb, and K. J. McManus. 2007. “Prediction of Water Pipe Asset Life Using Neural Networks.” Journal of Infrastructure Systems 13 (1): 26–30. doi:10.1061/(asce)1076-0342(2007)13:1(26).
   Web of Science ®Google Scholar
• Ahn, J. C., S. W. Lee, G. S. Lee, and J. Y. Koo. 2005. “Predicting Water Pipe Breaks Using Neural Network.” Water Science and Technology: Water Supply 5 (3–4): 159–172. doi:10.2166/ws.2005.0096.
   Google Scholar
• Akaike, H. 1973. “Information Theory and an Extension of the Maximum Likelihood Principle.” In Proceedings of the 2nd International Symposium on Information Theory, B. N. Petrov and F. Csaki edited by, 267–281. Budapest. doi:10.1007/978-1-4612-1694-0.
   Google Scholar
• Andreou, S. A., D. H. Marks, and R. M. Clark. 1987. “A New Methodology for Modelling Break Failure Patterns in Deteriorating Water Distribution Systems: Theory.” Advances in Water Resources 10 (1): 2–10. doi:10.1016/0309-1708(87)90002-9.
   Web of Science ®Google Scholar
• BBC. 2018. “Water Firms Failed Customers during ‘Beast from the East’” BBC News, June 19.
   Google Scholar
• Boxall, J. B., A. O’Hagan, S. Pooladsaz, A. J. Saul, and D. M. Unwin. 2007. “Estimation of Burst Rates in Water Distribution Mains.” In Proceedings of the Institution of Civil Engineers - Water Management, 160:73–82. doi:10.1680/wama.2007.160.2.73.
   Google Scholar
• Castillo, M.-C. M., D. González-Zeas, and L. Garrote. 2016. “Pressure as a Predictor of Occurrence of Pipe Breaks in Water Distribution Networks.” Urban Water Journal 13 (7): 676–686. Taylor Francis. doi:10.1080/1573062X.2015.1024687.
   Web of Science ®Google Scholar
• Chang, J. 2015. Package ‘Lda. R Software package. https://cran.r-project.org/web/packages/lda/lda.pdf
   Google Scholar
• Chen, T., and H. Tong. 2018. Xgboost: EXtreme Gradient Boosting. R software package. https://cran.r-project.org/web/packages/xgboost/vignettes/xgboost.pdf
   Google Scholar
• Christodoulou, S. 2011. “Water Network Assessment and Reliability Analysis by Use of Survival Analysis.” Water Resources Management; an International Journal - Published for the European Water Resources Association (EWRA) 25 (4): 1229–1238.
   Google Scholar
• Cortes, C., and V. Vapnik. 1995. “Support-Vector Networks.” Machine Learning 20 (3): 273–297. doi:10.1023/A:1022627411411.
   Web of Science ®Google Scholar
• De Silva, S. D., M. Moglia, P. Davis, and L. S. Burn. 2002. “Condition Assessment and Probabilistic Analysis to Estimate Failure Rates in Buried Pipelines.” 5th National Conference of the Australasian Society for Trenchless Technology. Sydney, Australia.
   Google Scholar
• Dehghan, A., K. J. McManus, and E. F. Gad. 2008. “Statistical Analysis of Structural Failures of Water Pipes.” Proceedings of the Institution of Civil Engineers - Water Management 161 (4): 207–214. doi:10.1680/wama.2008.161.4.207.
   Web of Science ®Google Scholar
• discoverwater. 2019. Loss of Supply. https://discoverwater.co.uk/loss-of-supply
   Google Scholar
• Enders, C. K. 2010. Applied Missing Data Analysis. New York: Guilford Press.
   Google Scholar
• Faris Hamdala, K., and G. Y. Sagar. 2016. “Statistical Analysis of Pipe Breaks in Water Distribution Systems in Ethiopia, the Case of Hawassa.” IOSR Journal of Mathematics (IOSR-JM) 12 (3): 127–136. doi:10.9790/5728-120304127136.
   Google Scholar
• Folkman, S. 2018. Water Main Break Rates in the USA and Canada: A Comprehensive Study. Utah State University. https://digitalcommons.usu.edu/mae_facpub/174
   Google Scholar
• Hoskins, A., and I. Stoianov. 2014. “InfraSense: A Distributed System for the Continuous Analysis of Hydraulic Transients.” Procedia Engineering 70 (2014): 823–832. doi:10.1016/j.proeng.2014.02.090.
   Google Scholar
• Hosmer, D. W., and S. Lemeshow. 2004. Applied Logistic Regression. 2nd ed. New York: John Wiley & Sons.
   Google Scholar
• Jacobs, P., and B. Karney. 1994. “GIS Development with Application to Cast Iron Water Main Breakage Rate.” 2nd International Conference in Water Pipeline Systems. Edinburgh, Scotland.
   Google Scholar
• Kabir, G., G. Demissie, R. Sadiq, and S. Tesfamariam. 2015. “Integrating Failure Prediction Models for Water Mains: Bayesian Belief Network Based Data Fusion.” Knowledge-Based Systems 85: 159–169. Elsevier B.V. doi: 10.1016/j.knosys.2015.05.002.
   Web of Science ®Google Scholar
• Kaushik, G., A. Manimaran, A. Vasan, and V. Sarangan. 2017. “Cracks under Pressure? Burst Prediction in Water Networks Using Dynamic Metrics.” Proceedings of the Twenty-Ninth AAAI Conference on Innovative Applications (IAAI-17)), Cracks, 4694–4700.
   Google Scholar
• Kecman, V. 2005. “Support Vector Machines – An Introduction.” In Support Vector Machines: Theory and Applications. Studies in Fuzziness and Soft Computing, edited by L. Wang. Berlin Heidelberg: Springer. doi:10.1007/10984697_1.
   Google Scholar
• Kettler, A. J., and I. C. Goulter. 1985. “An Analysis of Pipe Breakage in Urban Water Distribution Networks.” Canadian Journal of Civil Engineering 12 (2): 286–293. doi:10.1139/l85-030.
   Web of Science ®Google Scholar
• Kimutai, E., G. Betrie, R. Brander, R. Sadiq, and S. Tesfamariam. 2015. “Comparison of Statistical Models for Predicting Pipe Failures: Illustrative Example with the City of Calgary Water Main Failure.” Journal of Pipeline Systems Engineering and Practice 6 (4): 04015005/1–04015005/11. doi:10.1061/(ASCE)PS.1949-1204.0000196.
   Web of Science ®Google Scholar
• Kleiner, Y., and B. Rajani. 2002. “Forecasting Variations and Trends in Water-Main Breaks.” Journal of Infrastructure Systems 8 (4): 122–131. doi:10.1061/(ASCE)1076-0342(2002)8:4(122).
   Google Scholar
• Kleiner, Y., and B. Rajani. 2012. “Comparison of Four Models to Rank Failure Likelihood of Individual Pipes.” Journal of Hydroinformatics 14 (3): 659–681. doi:10.2166/hydro.2011.029.
   Web of Science ®Google Scholar
• Kutyłowska, M. 2016. “Support Vector Machines and Neural Networks for Forecasting of Failure Rate of Water Pipes.” In Proceedings of ECOpole 10: 41–46. doi:10.2429/proc.2016.10(1)005.
   Google Scholar
• Kutyłowska, M. 2017. “Prediction of Failure Frequency of Water-Pipe Network in the Selected City.” Periodica Polytechnica Civil Engineering 61 (3): 548–553. doi:10.3311/PPci.9997.
   Web of Science ®Google Scholar
• Kutyłowska, M. 2018. “K-Nearest Neighbours Method as a Tool for Failure Rate Prediction.” Periodica Polytechnica Civil Engineering 62 (2): 318–322. doi:10.3311/PPci.10045.
   Web of Science ®Google Scholar
• Kutyłowska, M. 2019. “Application of MARSplines Method for Failure Rate Prediction.” Periodica Polytechnica Civil Engineering 63 (1): 87–92. doi:10.3311/PPci.12559.
   Web of Science ®Google Scholar
• Le, G. Y., and P. Eisenbeis. 2000. “Using Maintenance Records to Forecast Failures in Water Networks.” Urban Water 2 (3): 173–181. doi:10.1016/S1462-0758(00)00057-1.
   Google Scholar
• Lei, J., and S. Sveinung. 1998. “Statistical Approach for Describing Failures and Lifetimes of Water Mains.” Water Science and Technology 38 (6): 209–217. doi:10.1016/S0273-1223(98)00582-4.
   Web of Science ®Google Scholar
• Liaw, A., and M. Wiener. 2002. “Classification and Regression by RandomForest Andy.” The Newsletter of the R Project News 2: 18–22.
   Google Scholar
• Loganathan, G. V., S. Park, and H. D. Sherali. 2002. “Threshold Break Rate for Pipeline Replacement in Water Distribution Systems.” Journal of Water Resources Planning and Management 128 (4): 271–279. doi:10.1061/(asce)0733-9496(2002)128:4(271).
   Web of Science ®Google Scholar
• Makar, J. M. 2000. “A Preliminary Analysis of Failures in Grey Cast Iron Water Pipes.” Engineering Failure Analysis 7 (1): 43–53. doi:10.1016/S1350-6307(99)00005-9.
   Web of Science ®Google Scholar
• McCullagh, P., and J. A. Nelder. 1989. Generalized Linear Models. 2nd ed. Florida, USA: Chapman and Hall/CRC.
   Google Scholar
• McMullen, L. D. 1982. “Advanced concepts in soil evaluation for exterior pipeline corrosion.” In AWWA Annual Conference. Miami, USA.
   Google Scholar
• Meyer, D., E. Dimiatriadou, K. Hornik, A. Weingessel, F. Leisch, C.-C. Chang, and C.-C. Lin. 2019. Package ‘E1071’. R Software package. https://cran.r-project.org/web/packages/e1071/e1071.pdf
   Google Scholar
• Moglia, M., P. Davis, and S. Burn. 2008. “Strong Exploration of a Cast Iron Pipe Failure Model.” Reliability Engineering and System Safety 93 (6): 885–896. doi:10.1016/j.ress.2007.03.033.
   Web of Science ®Google Scholar
• Molnar, C. 2018. “Iml: An R Package for Interpretable Machine Learning.” Journal of Open Source Software 32 (26): 786. doi:10.21105/joss.00786.
   Google Scholar
• Mordak, J., and J. Wheeler. 1988. Deterioration of Asbestos Cement Water Mains. Swindon, Wiltshire: WRc Engineering.
   Google Scholar
• Morrison, S. 2018. “London ‘Could Face Mass Water Shortage by 2040 if Ancient Pipes are Not Replaced’” EveningStandard. https://www.standard.co.uk/news/london/london-could-face-mass-water-shortage-by-2040-if-ancient-pipes-are-not-replaced-a3786126.html
   Google Scholar
• Ofwat. 2019. Final Determinations. Ofwat: Economic Regulator of the Water Sector in England and Wales.
   Google Scholar
• Pecci, F., E. Abraham, and I. Stoianov. 2017. “Scalable Pareto Set Generation for Multiobjective Co-Design Problems in Water Distribution Networks: A Continuous Relaxation Approach.” Structural and Multidisciplinary Optimization 55 (3): 857–869. doi:10.1007/s00158-016-1537-8.
   Web of Science ®Google Scholar
• Pelletier, G., A. Mailhot, and J.-P. Villeneuve. 2003. “Modeling Water Pipe Breaks—Three Case Studies.” Journal of Water Resources Planning and Management 129 (2): 115–123. doi:10.1061/(asce)0733-9496(2003)129:2(115).
   Web of Science ®Google Scholar
• Poulton, M., and B. Bremond. 2007. “The Impact of Pipe Segment Length on Break Predictions in Water Distribution Systems.” 2nd Leading Edge Conference on Strategic Asset Management, 1–11. Lisbon, Portugal.
   Google Scholar
• Qi, Z., F. Zheng, D. Guo, T. Zhang, Y. Shao, Y. Tingchao, K. Zhang, and H. R. Maier. 2018b. “A Comprehensive Framework to Evaluate Hydraulic and Water Quality Impacts of Pipe Breaks on Water Distribution Systems.” Water Resources Research 54 (10): 8174–8195. doi:10.1029/2018WR022736.
   Web of Science ®Google Scholar
• Qi, Z., F. Zheng, H. R. Danlu Guo, T. Z. Maier, Y. Tingchao, and Y. Shao. 2018a. “Better Understanding of the Capacity of Pressure Sensor Systems to Detect Pipe Burst within Water Distribution Networks.” Journal of Water Resources Planning and Management 144 (7): 1–11. doi:10.1061/(ASCE)WR.1943-5452.0000957.
   Web of Science ®Google Scholar
• Rajani, B., and Y. Kleiner. 2001. “Comprehensive Review of Structural Deterioration of Water Mains: Physically Based Models.” Urban Water 3 (3): 151–164. doi:10.1016/S1462-0758(01)00033-4.
   Google Scholar
• Rezaei, H., B. Ryan, and I. Stoianov. 2015. “Pipe Failure Analysis and Impact of Dynamic Hydraulic Conditions in Water Supply Networks.” 13th Computer Control for Water Industry Conference, CCWI 2015, 119: 253–262. doi:10.1016/j.proeng.2015.08.883.
   Google Scholar
• Røstum, J. 2000. “Statistical Modelling of Pipe Failures in Water Networks.” PhD Thesis.
   Google Scholar
• Sadiq, R., B. Rajani, and Y. Kleiner. 2004. “Fuzzy-Based Method to Evaluate Soil Corrosivity for Prediction of Water Main Deterioration.” Journal of Infrastructure Systems 10 (4): 149–156. doi:10.1061/(asce)1076-0342(2004)10:4(149).
   Google Scholar
• Scheidegger, A., J. P. Leitão, and L. Scholten. 2015. “Statistical Failure Models for Water Distribution Pipes - A Review from A Unified Perspective.” Water Research 83: 237–247. doi:10.1016/j.watres.2015.06.027.
   PubMed Web of Science ®Google Scholar
• Shamir, U., and C. Howard. 1979. “An Analytical Approach to Scheduling Pipe Replacement.” Journal-American Water Works Association 71 (5): 248–258. doi:10.1002/j.1551-8833.1979.tb04345.x.
   Web of Science ®Google Scholar
• St. Clair, A. M., and S. Sinha. 2012. “State-of-the-Technology Review on Water Pipe Condition, Deterioration and Failure Rate Prediction Models!” Urban Water Journal 9 (2): 85–112. doi:10.1080/1573062X.2011.644566.
   Web of Science ®Google Scholar
• Stoianov, I., L. Nachman, S. Madden, and T. Tokmouline. 2007. “PIPENETa Wireless Sensor Network for Pipeline Monitoring.” IPSN 2007: Proceedings of the Sixth International Symposium on Information Processing in Sensor Networks, 264–273. doi:10.1145/1236360.1236396.
   Google Scholar
• Tsitsifli, S., V. Kanakoudis, Y. Bakouros, and P. Areos. 2006. “Pipe Reliability Assessment Using Discriminant Analysis and Classification : A Case Study from Mexico.” In Protection and Restoration of the Environment VIII, edited by E. Gidarakos, N. Nikolaidis, and C. Christodoulatos, 1–8. Chania, Crete. https://www.researchgate.net/publication/258983030_Pipe_reliability_assessment_using_discriminant_analysis_and_classification_a_case_study_from_Mexico
   Google Scholar
• Vanrenterghem-Raven, A. 2007. “Risk Factors of Structural Degradation of an Urban Water Distribution System.” Journal of Infrastructure Systems 13 (1): 55–64. doi:10.1061/(ASCE)1076-0342(2007)13:1(55).
   Web of Science ®Google Scholar
• Venables, W. 2016. Package ‘Nnet’. R Software package. https://cran.r-project.org/web/packages/nnet/nnet.pdf
   Google Scholar
• Walski, T. M., and A. Pelliccia. 1982. “Economic Analysis of Water Main Breaks.” Journal of American Water Works Association 74 (3): 140–147. doi:10.1002/j.1551-8833.1982.tb04874.x.
   Web of Science ®Google Scholar
• Winkler, D., M. Haltmeier, M. Kleidorfer, W. Rauch, and F. Tscheikner-gratl. 2018. “Pipe Failure Modelling for Water Distribution Networks Using Boosted Decision Trees.” Structure and Infrastructure Engineering 14 (10): 1402–1411. doi:10.1080/15732479.2018.1443145.
   Web of Science ®Google Scholar
• Wood, A., and B. J. Lence. 2009. “Using Water Main Break Data to Improve Asset Management for Small and Medium Utilities: District of Maple Ridge, B.C.” Journal of Infrastructure Systems 15 (2): 111–119. doi:10.1061/(ASCE)1076-0342(2009)15:2(111).
   Web of Science ®Google Scholar
• Wright, J. R. 2011. Spatial Decision Support for Estimating the Pipe-Break Vulnerabilities in Water Distribution Mains. MEng diss, Imperial College London
   Google Scholar
• Yamijala, S., S. D. Guikema, and K. Brumbelow. 2009. “Statistical Models for the Analysis of Water Distribution System Pipe Break Data.” Reliability Engineering and System Safety 94 (2): 282–293. doi:10.1016/j.ress.2008.03.011.
   Web of Science ®Google Scholar
• Zeileis, A., C. Kleiber, and S. Jackman. 2015. “Regression Models for Count Data in R.” Journal of Statistical Software. doi:10.18637/jss.v027.i08.
   Web of Science ®Google Scholar