Neural Computing and Applications

, Volume 31, Issue 1, pp 157–169 | Cite as

Extreme learning machine model for water network management

  • Ahmed M. A. Sattar
  • Ömer Faruk Ertuğrul
  • B. GharabaghiEmail author
  • E. A. McBean
  • J. Cao
Original Article


A novel failure rate prediction model is developed by the extreme learning machine (ELM) to provide key information needed for optimum ongoing maintenance/rehabilitation of a water network, meaning the estimated times for the next failures of individual pipes within the network. The developed ELM model is trained using more than 9500 instances of pipe failure in the Greater Toronto Area, Canada from 1920 to 2005 with pipe attributes as inputs, including pipe length, diameter, material, and previously recorded failures. The models show recent, extensive usage of pipe coating with cement mortar and cathodic protection has significantly increased their lifespan. The predictive model includes the pipe protection method as pipe attributes and can reflect in its predictions, the effect of different pipe protection methods on the expected time to the next pipe failure. The developed ELM has a superior prediction accuracy relative to other available machine learning algorithms such as feed-forward artificial neural network that is trained by backpropagation, support vector regression, and non-linear regression. The utility of the models provides useful inputs when planning and budgeting for watermain inspection, maintenance, and rehabilitation.


Water pipe network Pipe failure Extreme machine learning Management tool 



The authors would like to thank the district of Scarborough for their contribution in the data collection phase and funding by the Natural Sciences and Engineering Research Council of Canada and the Canada Research Chairs program.

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. 1.
    Sattar AM, Gharabaghi B, McBean E (2016) Predicting timing of watermain failure using gene expression models for infrastructure planning. Water Resour Manag 30(5):1635–1651CrossRefGoogle Scholar
  2. 2.
    Schuster C, McBean E (2008) Impacts of cathodic protection on pipe break probabilities: a Toronto case study. Can J Civ Eng 35(2):210–216CrossRefGoogle Scholar
  3. 3.
    Nishiyama M, Filion Y (2013) Review of statistical water main break prediction models. Can J Civ Eng 40:972–979CrossRefGoogle Scholar
  4. 4.
    Kleiner Y, Sadiq R, Rajani B (2006) Modelling the deterioration of buried infrastructure as a fuzzy Markov process. J Water Supply Res Technol AQUA 55(2):67–80CrossRefGoogle Scholar
  5. 5.
    Huang G, Zhu Y, Siew C (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501CrossRefGoogle Scholar
  6. 6.
    Atieh M, Mehltretter S, Gharabaghi B, Rudra R (2015a) Integrated neural networks model for prediction of sediment rating curve parameters for ungauged basins. J Hydrol 531(3):1095–1107. doi: 10.1016/j.jhydrol.2015.11.008 CrossRefGoogle Scholar
  7. 7.
    Atieh M, Gharabaghi B, Rudra R (2015b) Entropy-based neural networks model for flow duration curves at ungauged sites. J Hydrol 529(3):1007–1020. doi: 10.1016/j.jhydrol.2015.08.068 CrossRefGoogle Scholar
  8. 8.
    Atieh, M., Taylor, G., Sattar, A. M., & Gharabaghi, B. (2017). Prediction of flow duration curves for ungauged basins. Journal of Hydrology. Volume 545, February 2017, Pages 383–394, DOI:  10.1016/j.jhydrol.2016.12.048.
  9. 9.
    Cao J, Xiong X (2014) Protein sequence classification with improved extreme learning machine algorithms. Biomed Res Int. doi: 10.1155/2014/103054. Epub 2014 Mar 30Google Scholar
  10. 10.
    Ding S, Zhang J, Xu X, Yanan Z (2015) A wavelet extreme learning machine. Neural Comput & Applic 27(4):1033–1040CrossRefGoogle Scholar
  11. 11.
    Ding SF, Xu XZ, Nie R (2014) Extreme learning machine and its applications. Neural Comput. Appl 25(3):549–556CrossRefGoogle Scholar
  12. 12.
    Ertugrul O, Kaya M (2014) A detailed analysis on extreme learning machine and novel approaches based on ELM. American Journal of Computer Science and Engineering 1(5):43–50Google Scholar
  13. 13.
    Gazendam, E., Gharabaghi, B., Ackerman, J., & Whiteley, H. (2016). Integrative neural networks models for stream assessment in restoration projects. Journal of Hydrology, 536 (2016) 339-350. DOI:  10.1016/j.jhydrol.2016.02.057.
  14. 14.
    Lian C, Zeng Z, Yao W, Tang H (2014) Ensemble of extreme learning machine for landslide displacement prediction based on time series analysis. Neural Comput & Applic 24(1). doi: 10.1007/s00521
  15. 15.
    Luo M, Zhang K (2014) A hybrid approach combining extreme learning machine and sparse representation for image classification. Journal Engineering Applications of Artificial Intelligence archive 27:228–235CrossRefGoogle Scholar
  16. 16.
    Man Z, Huang G (2016) Guest editorial: special issue of extreme learning machine and applications. Neural Comput & Applic 27(1):1–2CrossRefGoogle Scholar
  17. 17.
    Sabouri F, Gharabaghi B, Sattar A, Thompson AM (2016) Event-based stormwater management pond runoff temperature model. Journal of Hydrology 540(2016):306–316. doi: 10.1016/j.jhydrol.2016.06.017 CrossRefGoogle Scholar
  18. 18.
    Trenouth WR, Gharabaghi B (2016) Highway runoff quality models for the protection of environmentally sensitive areas. Journal of Hydrology Volume 542(November 2016):143–155CrossRefGoogle Scholar
  19. 19.
    Cao J, Lin Z, Huang G, Liu N (2012) Voting based extreme learning machine. Inf Sci 185(1):66–77MathSciNetCrossRefGoogle Scholar
  20. 20.
    Huang G, Zhou Y, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern B Cybern 42(2):513–529CrossRefGoogle Scholar
  21. 21.
    Storn R, Price K (1997) Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. J Glob Optim 11(4):341–359MathSciNetCrossRefzbMATHGoogle Scholar
  22. 22.
    Sattar AM (2014a) Gene expression models for the prediction of longitudinal dispersion coefficients in transitional and turbulent pipe flow. J. Pipeline Syst. Eng. Pract. ASCE 5(1):04013011CrossRefGoogle Scholar
  23. 23.
    Sattar AM (2016b) A probabilistic projection of the transient flow equations with random system parameters and internal boundary conditions. J Hydraul Res. doi: 10.1080/00221686.2016.1140682 Google Scholar
  24. 24.
    Sattar AM, Gharabaghi B (2015) Gene expression models for prediction of longitudinal dispersion coefficient in streams. J Hydrol 524:587–596CrossRefGoogle Scholar
  25. 25.
    Al-Barqawi M, Zayed T (2006) Condition rating model for underground infrastructure sustainable water mains. Journal of Performance of Constructed Facilities, ASCE. 20(2):126–135CrossRefGoogle Scholar
  26. 26.
    El Hakeem M, Sattar AM (2015) An entrainment model for non-uniform sediment. Earth Surf Process Landf. doi: 10.1002/esp.3715 Google Scholar
  27. 27.
    Najafzadeh M, Sattar AM (2015) Neuro-fuzzy GMDH approach to predict longitudinal dispersion in water networks. Water Resour Manag 29:2205–2219. doi: 10.1007/s11269-015-0936-8 CrossRefGoogle Scholar
  28. 28.
    Sattar AM, Dickerson J, Chaudhry M (2009) A wavelet Galerkin solution to the transient flow equations. J Hydraul Eng 135(4):283–295CrossRefGoogle Scholar
  29. 29.
    Sattar AM (2016a) Prediction of organic micropollutant removal in soil aquifer treatment system using GEP. J Hydrol Eng. doi: 10.1061/(ASCE)HE.1943-5584.0001372 (in press) Google Scholar
  30. 30.
    Thompson J, Sattar A, Gharabaghi B, Warner R (2016) Event-based total suspended sediment particle size distribution model. J Hydrol 536(2016):236–246CrossRefGoogle Scholar
  31. 31.
    Vose D (1996) Quantitative risk analysis: a guide to Monte Carlo simulation modeling. John Wiley, New YorkzbMATHGoogle Scholar
  32. 32.
    Walker H (1931) Studies in the history of the statistical method. Williams & Wilkins Co., Baltimore, MD, pp 24–25Google Scholar
  33. 33.
    Folkman S (2012) Water main break rates in the USA and Canada: a comprehensive study, report, Utah State University buried structures laboratory, April 2012.Google Scholar
  34. 34.
    Rajani B, Kleiner Y, Sink JE (2012) Exploration of the relationship between water main breaks and temperature covariates. Urban Water 9(2):67–84CrossRefGoogle Scholar
  35. 35.
    Harvey R, McBean EA, Murphy HM, Gharabaghi B (2015) Using data mining to understand drinking water advisgories in small water systems: a case study of Ontario first nations drinking water supplies. Water Resources Management 29(14):5129–5139CrossRefGoogle Scholar
  36. 36.
    Harvey R, McBean E, Gharabaghi B (2014) Predicting the timing of water main failure using artificial neural networks. J Water Resour Plan Manag 140(4):425–434CrossRefGoogle Scholar
  37. 37.
    Harvey R, McBean EA, Gharabaghi B (2013) Predicting the timing of watermain failure using artificial neural networks. J Water Resour Plan Manag 140(4):425–434CrossRefGoogle Scholar
  38. 38.
    Verbeeck H, Samson R, Verdonck F, Raoul L (2006) Parameter sensitivity and uncertainty of the forest carbon flux model FOUG: a Monte Carlo analysis. Tree Physiol 26:807–817CrossRefGoogle Scholar
  39. 39.
    Goulter IC, Kazemi A (1998) Spatial and temporal groupings of water main pipe breakage in Winnipeg. Can J Civ Eng 15(1):91–97CrossRefGoogle Scholar
  40. 40.
    Asnaashari A, McBean EA, Gharabaghi B, Tutt D (2013) Forecasting watermain failure using artificial neural network modeling. Canadian Water Resources Journal 38(1):24–33CrossRefGoogle Scholar
  41. 41.
    Asnaashari A, McBean E, Gharabaghi B, Pourrajab R, Shahrour I (2010) Survival rate analyses of watermains: a comparison of case studies for Canada and Iran. Journal of Water Management Modeling 18(30):499–508Google Scholar
  42. 42.
    Asnaashari A, McBean EA, Shahrour I, Gharabaghi B (2009) Prediction of watermain failure frequencies using multiple and Poisson regression. Water Sci Technol Water Supply 9(1):9–19CrossRefGoogle Scholar
  43. 43.
    Rostum J (2000) Master of Science Dissertation. In: Statistical modeling of pipe failures in water networks. Norwegian University of Science and Technology, Trondheim, NorwayGoogle Scholar
  44. 44.
    Lei J (1997) Statistical approach for describing lifetimes of water mains - case Trondheim Municpality. STF22 A97320, SINTEF, Trondheim.Google Scholar
  45. 45.
    Wang Y, Moselhi O, Zayed T (2009) Study of the suitability of existing deterioration models for water mains. Journal of Performance of Constructed Facilities, ASCE 23(1):40–46Google Scholar
  46. 46.
    Sattar AM (2014b) Gene expression models for prediction of dam breach parameters. Journal of Hydroinformatics, IWA 16(3):550–571CrossRefGoogle Scholar
  47. 47.
    Sattar AMA, El-Beltagy M (2017) Stochastic Solution to the Water Hammer Equations Using Polynomial Chaos Expansion with Random Boundary and Initial Conditions. J Hydraul Eng 143(2):04016078Google Scholar
  48. 48.
    Ebtehaj I, Sattar AMA, Bonakdari H, Zaji AH (2017) Prediction of scour depth around bridge piers using self-adaptive extreme learning machine. J Hydroinf 19(2):207–224Google Scholar

Copyright information

© The Natural Computing Applications Forum 2017

Authors and Affiliations

  1. 1.Department of Irrigation & Hydraulics, Faculty of EngineeringCairo UniversityGizaEgypt
  2. 2.Department of Electrical and Electronics EngineeringBatman UniversityBatmanTurkey
  3. 3.School of EngineeringUniversity of GuelphGuelphCanada
  4. 4.Institute of Information and ControlHangzhou Dianzi UniversityZhejiangChina

Personalised recommendations