Abstract
The deterioration of aging sanitary sewer pipes poses a potentially significant environmental and economic threat. While accurate information on sewer condition required for proactive management can be obtained through closed-circuit television (CCTV) inspections, these inspections are expensive and hence frequently limited to relatively small portions of the sewer system. Hence, there is real value in alternatives to assist in determining sewer integrity. Data mining is demonstrated as a means of extracting information from limited inspection records, allowing sewer pipe condition to be predicted for pipes that have not yet been inspected. The paper describes a classification tree algorithm capable of providing insight into a pipe condition dataset obtained after inspecting a portion of the sanitary sewers in Guelph, Ontario, Canada. The model is developed with minimal data pre-processing effort and illustrates the influence of pipe-specific attributes (e.g. year of construction, diameter and length) on pipe condition in a format that can be easily shared with those unfamiliar with the data mining process. The predictive capability of the classification tree is validated using a stratified test set representative of the distribution of pipe condition existing in the sewer system. CCTV inspection datasets are often imbalanced—with significantly more pipes in one condition class than another and this is problematic as data mining algorithms tend to be most effective when observations available for model development are balanced across classes. An optimally tuned classification tree predicts binary pipe condition (good vs. poor condition) with an overall accuracy of 76 % (282 out of 364 instances of pipe condition correctly predicted in the stratified test set). The model achieved an acceptable test set area under the receiver operating characteristic (ROC) curve of 0.77 and can effectively identify individual pipes for future rounds of inspection. The data mining approach presented herein is found capable of unlocking information contained within inspection records and enhances existing management practices used in the wastewater industry.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ana E (2009) Sewer asset management—sewer structural deterioration modeling and multi-criteria decision making in sewer rehabilitation projects prioritization. Vrije Universiteit Brussel, Brussels
Ana EV, Bauwens W (2010) Modeling the structural deterioration of urban drainage pipes. Urban Water J 79:1069–1079
ASCE (2013) America’s infrastructure report card. American Society of Civil Engineers
Atef A, Osman H, Moselhi O (2012) Multi-objective genetic algorithm to allocate budegtary resources for condition assessment of water and sewer networks. Can J Civ Eng 39(9):978–992
Breiman L, Friedman J, Olshen R, Stone C (1984) Classification and regression trees. Wadsworth International Group, Belmont
Carlson NR, Urquhart SA (2006) A sewer sinkhole study using TEM. Lead Edge 25:348–350
Davies J, Clarke B, Whiter J, Cunningham R (2001) Factors influencing the structural deterioration and collapse of rigid sewer pipes. Urban Water J 3(1):73–89
Doshi J (2012) An investigation of leaky sewers as a source of fecal contamination in the stormwater drainage systems in Singapore. Massachusetts Institute of Technology
Duchesne S, Beardsell G, Villeneuve JP, Trombou B, Bouchard K (2012) A susrval analysis model for sewer pipe structural deterioration. Comput Aided Civ Infrastruct Eng 28(2):146–160
EPA (2002) The clean water and drinking water infrastructure gap analysis. United States Environmental Protection Agency
EPA (2010) Condition assessment of wastewater collection systems. United States Environmental Protection Agency
Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27(8):861–874
Han J, Kamber M, Pei J (2006) Data mining—concepts and techniques, 3rd edn. Morgan Kaufmann Publishers, CA
Heywood G, Pearman C, Lumbers J (2007) Advances in the modelling and optimization of sewerage infrastructure investment planning. In: International water association leading conference on strategic asset management, Lisbon, pp 1–14
Hosmer D, Lemeshow S (2000) Applied logistic regression. Wiley, New York
Jung J, Garrett JH, Soibelman L, Lipkin K (2012) Application of classification models and spatial clustering analysis to a sewage collection system of a mid-sized city. In: Issa R (ed) International conference on computing in civil engineering, Clearwater Beach, Florida, ASCE, pp 537–544
Khan Z, Zayed T, Moselhi O (2010) Structural condition assessment of sewer pipelines. J Perform Construct Facil 24(2):170–179
Kley G, Caradot N (2013) Review of sewer deterioration models—project SEMA—technical report prepared for Kompetenzzentrum Berlin GmbH. Veolia Water, Berlin
Koo D, Ariaratnam S (2006) Innovative method for assessment of underground sewer pipe condition. Autom Constr 15(4):479–488
Kuhn M (2013) The caret package. http://caret.r-forge.r-project.org/. Accessed 1 Oct 2013
Kuhn M, Johnson K (2013) Applied predictive modeling, 1st edn. Springer Science and Business Media, New York
LeGat Y (2006) Modeling the deterioration process of drainage pipelines. Urban Water J 5:97–106
Mashford J, Marlow D, Tran D, May R (2011) Prediction of sewer condition grade using support vector machines. J Comput Civ Eng 25(4):283–290
Micevski T, Kuczera G, Coombes P (2002) Markov model for stormwater pipe deterioration. J Infrastruct Syst 8(2):49–56
Salman B (2010) Infrastructure management and deterioration risk assessment of wastewater collection systems. University of Cincinnati, Ohio
Sercu B, Werfhorst LVD, Murray J, Holden P (2011) Sewage exfiltration as a source of storm drain contamination during dry weather in urban watersheds. Environ Sci Technol 45(17):7151–7157
Therneau T, Atkinson B, Ripley B (2014) The rpart package. Technical report. The rpart package. http://cran.r-project.org/web/packages/rpart/rpart.pdf
Tran D (2007) Investigations of deterioration models for stormwater pipelines. Victoria University, Australia
Tran D, Ng A, McManus K, Burns S (2008) Prediction models for serviceability deterioration of stormwater pipes. Struct Infrastruct Eng 4:287–295
Wolpert D, Macready W (1997) No free lunch theorems for optimization. IEEE Trans Evol Comput 1:67–82
WRc (1996) Manual of sewer condition classification, 3rd edn. Water Research Centre, Swindon
Younis R, Knight M (2010) A probability model for investigating the trend of structural deterioration in wastewater pipelines. Tunn Undergr Space Technol 25(6):670–680
Acknowledgments
The authors would like to thank the City of Guelph for the provision of the sanitary sewer inspection records and assistance throughout the research process. Thank you to Adam Bonnycastle and the Department of Geography at the University of Guelph for assistance with GIS analysis. The University of Guelph, the Natural Sciences and Engineering Council of Canada and the Canada Research Chairs program funded this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Harvey, R., McBean, E. (2015). A Data Mining Tool for Planning Sanitary Sewer Condition Inspection. In: Hipel, K., Fang, L., Cullmann, J., Bristow, M. (eds) Conflict Resolution in Water Resources and Environmental Management. Springer, Cham. https://doi.org/10.1007/978-3-319-14215-9_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-14215-9_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-14214-2
Online ISBN: 978-3-319-14215-9
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)