Skip to main content
View expanded cover

Securing Water and Wastewater Systems pp 107–122Cite as

Implementing Machine Learning Algorithms for Water Quality Event Detection: Theory and Practice

Part of the Protecting Critical Infrastructure book series (PCIN,volume 2)

Abstract

The current chapter examines the implementation of machine learning for water quality event detection. Two alternatives—supervised and unsupervised - are examined. It can be seen that the former performs better with the existence of historical classified true events, while the latter is preferable when history is not a factor. Water properties and their influence on methodology performance are also examined. The paper explains that TOC is preferred when false negative errors are rare or when experts' probability to make mistakes is low. The manuscript provides a numerical example that illustrates the two above-mentioned methodologies.

Keywords

  • False Alarm
  • Receiver Operating Characteristic Curve
  • United States Environmental Protection Agency
  • Unsupervised Learning
  • Water Utility

These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

This is a preview of subscription content, access via your institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-319-01092-2_4
  • Chapter length: 16 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   109.00
Price excludes VAT (USA)
  • ISBN: 978-3-319-01092-2
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   139.99
Price excludes VAT (USA)
Hardcover Book
USD   139.99
Price excludes VAT (USA)
Learn about institutional subscriptions
Fig. 4.1
Fig. 4.2
Fig. 4.3
Fig. 4.4
Fig. 4.5
Fig. 4.6
Fig. 4.7
Fig. 4.8

Notes

  1. 1.

    Results from this project have been presented at the annual American Water Works Association conference in 2011, but the official report has not yet been published.

  2. 2.

    http://www.cs.waikato.ac.nz/ml/weka/.

Abbreviations

AWWA:

American Water Works Associations

DT:

Decision tree

EDS:

Event detection system

LR:

Logistic regression

ML:

Machine learning

NN:

Neural network

USEPA:

Environmental Protection Agency

WQE:

Water quality event

WQED:

Water quality event detection

References

  • Berman O, Gavious A (2007) Location of terror response facilities: a game between state and terrorist. Eur J Oper Res 177(2007):1113–1133

    CrossRef  Google Scholar 

  • Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Chapman & Hall/CRC, New York

    Google Scholar 

  • Chang N-B, Pongsanone NP, Ernest A (2012) A rule-based decision support system for sensor deployment in small drinking water networks. J Cleaner Prod 29–30:28–37

    Google Scholar 

  • Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psychol Measur 20(1):37–46

    CrossRef  Google Scholar 

  • EPA (2005) WaterSentinel online water quality monitoring as an indicator of drinking water contamination. EPA 817-D-05-002

    Google Scholar 

  • Helbling DE, VanBriesen JM (2008) Continuous monitoring of residual chlorine concentrations in response to controlled microbial intrusions in a laboratory-scale distribution system. Water Res 42(12):3162–3172

    Google Scholar 

  • Mann J, Runge J (2010) State of the industry report 2010: how water professionals are meeting ongoing challenges and economic uncertainty. J AWWA 102:10

    Google Scholar 

  • Quinlan JR (1986) Induction of decision trees. Mach Learn 1:81–106

    Google Scholar 

  • Quinlan JR (1993) C4.5: programs for machine learning. Morgan Kaufmann Publishers, San Francisco

    Google Scholar 

  • Skadsen J (2008) Distribution system on-line monitoring for detecting contamination and water quality changes. J AWWA 100:7

    Google Scholar 

  • Story MS, Van der Gaag B, Burns B (2011) Advances in on-line drinking water quality monitoring and early warning systems. Water Res 45:741–747

    Google Scholar 

  • Yang YJ, Haught RC, Goodrich JA (2009) Real-time contaminant detection and classification in a drinking water pipe using conventional water quality sensors: techniques and experimental results. J Environ Manage 90(8):2494–2506

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Technology Management (MOT), Holon Institute of Technology, Holon, Israel

    Eyal Brill

Authors
  1. Eyal Brill
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Eyal Brill .

Editor information

Editors and Affiliations

  1. Environmental Engineering and Public Heath Consultant, Cincinnati, Ohio, USA

    Robert M. Clark

  2. Department of Economics, Temple University, Philadelphia, Pennsylvania, USA

    Simon Hakim

Appendix A

Appendix A

Following is a list of websites for common EDS systems

Gardian Blue by Hach: http://hachhst.com/products/cityguard-virtual-command-center

Canary by Sandia Labs: https://share.sandia.gov/news/resources/news_releases/canary/

Moni::tool by S::can: http://www.s-can.at/

BlueBox by WhiteWater: http://www.w-water.com/qualitysecurity/Product.aspx?id=64

Rights and permissions

Reprints and Permissions

Copyright information

© 2014 Springer International Publishing Switzerland

About this chapter

Cite this chapter

Brill, E. (2014). Implementing Machine Learning Algorithms for Water Quality Event Detection: Theory and Practice. In: Clark, R., Hakim, S. (eds) Securing Water and Wastewater Systems. Protecting Critical Infrastructure, vol 2. Springer, Cham. https://doi.org/10.1007/978-3-319-01092-2_4

Download citation