Supervised Machine Learning Approaches for Leak Localization in Water Distribution Systems: Impact of Complexities of Leak Characteristics
Publication: Journal of Water Resources Planning and Management
Volume 149, Issue 8
Abstract
Localizing pipe leaks is a significant challenge for water utilities worldwide. Pipe leaks in water distribution systems (WDSs) can cause the loss of a large amount of treated water, leading to pressure loss, increased energy costs, and contamination risks. What makes localizing pipe leaks challenging is the underground location of the water pipes and the similarity in impact on hydraulic properties (e.g., pressure, flow) due to leaks as compared to the effects of WDS operational changes. Physical methods to locate leaks are expensive, intrusive, and heavily localized. Computational approaches such as data-driven machine learning models provide an economical alternative to physical methods. Machine learning models are readily available and easily customizable to most problems; therefore, there is an increasing trend in their application for leak localization in WDSs. While several studies have applied machine learning models to localize leaks in single pipes and small test networks, these studies have yet to thoroughly test these models against the different complexities of leak localization problems, and hence their applicability to real-world WDSs is still unclear. The simplicity of the WDSs, the oversimplification of leak characteristics, and the lack of consideration of modeling and measuring device uncertainties adopted in most of these studies make the scalability of their proposed approaches questionable to real-world WDSs. Our study addresses this issue by devising four study cases of different complexity that account for realistic leak characteristics and model- and measuring device-related uncertainties. Two established machine learning models—multilayer perceptron (MLP) and convolutional neural network (CNN)—are trained and tested for their ability to localize the leaks and predict their sizes for each of the four study cases using different simulated hydraulic inputs. In addition, the potential benefit of combining different types of hydraulic data as inputs to the machine learning models in localizing leaks is also explored. Pressure and flow, two common hydraulic measurements, are used as inputs to the machine learning models. Further, the impact of single and multiple time point input in leak localization is also investigated. The results for the L-Town network indicate good accuracies for both the models for all study cases, with CNN consistently outperforming MLP.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code that support the findings of this study are available from the corresponding author upon reasonable request, including pressure, flow, and leak response data for the four cases presented in this study.
Acknowledgments
This material is based upon work supported by the National Science Foundation (NSF) under Partnership for Innovation (PFI) Grant No. 1919228.
References
Abadi, M., et al. 2016. “Tensor flow: Large-scale machine learning on heterogeneous distributed systems.” Accessed December 13, 2022. https://arxiv.org/abs/1603.04467.
Abdulla, M. B., and R. Herzallah. 2015. “Probabilistic multiple model neural network based leak detection system: Experimental study.” J. Loss Prev. Process Ind. 36 (Jul): 30–38. https://doi.org/10.1016/j.jlp.2015.05.009.
Berglund, A., V. S. Areti, D. Brill, and G. K. Mahinthakumar. 2017. “Successive linear approximation methods for leak detection in water distribution systems.” J. Water Resour. Plann. Manage. 143 (8): 1–13. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000784.
Blesa, J., and R. Pérez. 2018. “Modelling uncertainty for leak localization in water networks.” IFAC-Pap. Online 51 (24): 730–735. https://doi.org/10.1016/j.ifacol.2018.09.656.
Bohorquez, J., B. Alexander, A. R. Simpson, and M. F. Lambert. 2020. “Leak detection and topology identification in pipelines using fluid transients and artificial neural networks.” J. Water Resour. Plann. Manage. 146 (6): 04020040. https://doi.org/10.1061/(ASCE)WR.1943-5452.0001187.
Eliades, D. G., M. Kyriakou, S. Vrachimis, and M. M. Polycarpou. 2016. EPANET-MATLAB toolkit: An open-source software for interfacing EPANET with MATLAB. Amsterdam, Netherlands: Computer Control for Water Industry. https://doi.org/10.5281/zenodo.437751.
Fontanazza, C. M., V. Notaro, V. Puleo, P. Nicolosi, and G. Freni. 2015. “Contaminant intrusion through leaks in water distribution system: Experimental analysis.” Procedia Eng. 119 (1): 426–433. https://doi.org/10.1016/j.proeng.2015.08.904.
Goodfellow, I., Y. Bengio, and A. Courville. 2016. Deep learning. Cambridge, MA: MIT Press.
Hu, Z., D. Tan, B. Chen, W. Chen, and D. Shen. 2021. “Review of model-based and data-driven approaches for leak detection and location in water distribution systems.” Water Supply 21 (7): 3282–3306. https://doi.org/10.2166/ws.2021.101.
Kingma, D. P., and J. L. Ba. 2014. “Adam: A method for stochastic optimization.” Preprint, submitted December 13, 2022. https://arxiv.org/abs/1412.6980.
Klise, K. A., M. Bynum, D. Moriarty, and R. Murray. 2017. “A software framework for assessing the resilience of drinking water systems to disasters with an example earthquake case study.” Environ. Modell. Software 95 (Sep): 420–431. https://doi.org/10.1016/j.envsoft.2017.06.022.
Krizhevsky, A., I. Sutskever, and G. E. Hinton. 2017. “ImageNet classification with deep convolutional neural networks.” Commun. ACM 60 (6): 84–90. https://doi.org/10.1145/3065386.
Lan, R., H. Zou, C. Pang, Y. Zhong, Z. Liu, and X. Luo. 2021. “Image denoising via deep residual convolutional neural networks.” Signal Image Video Process. 15 (1): 1–8. https://doi.org/10.1007/s11760-019-01537-x.
LeCun, Y., B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel. 1990. “Handwritten digit recognition with a back-propagation network.” In Advances in neural information processing systems, 2. Denver: Morgan Kaufmann.
LeCun, Y., L. Bottou, Y. Bengio, and P. Haffner. 1998. “Gradient-based learning applied to document recognition.” Proc. IEEE 86 (11): 2278–2324. https://doi.org/10.1109/5.726791.
Liemberger, R., and A. Wyatt. 2019. “Quantifying the global non-revenue water problem.” Water Sci. Technol. Water Supply 19 (3): 831–837. https://doi.org/10.2166/ws.2018.129.
Lloyd, S. P. 1982. “Least squares quantization in PCM.” IEEE Trans. Inf. Theory 28 (2): 129–137. https://doi.org/10.1109/TIT.1982.1056489.
Lučin, I., Z. Carija, S. Druzeta, and B. Lučin. 2021. “Detailed leak localization in water distribution networks using random forest classifier and pipe segmentation.” IEEE Access 9 (Nov): 155113–155122. https://doi.org/10.1109/ACCESS.2021.3129703.
Maas, A. L., and A. Y. Ng. 2013. “Rectifier nonlinearities improve neural network acoustic models.” In Proc., 30th Int. Conf. on Machine Learning, 28. Stanford, CA: Stanford Univ.
Mashford, J., D. D. Silva, S. Burn, and D. Marney. 2012. “Leak detection in simulated water pipe networks using SVM.” Appl. Artif. Intell. 26 (5): 429–444. https://doi.org/10.1080/08839514.2012.670974.
Mohammed, E. G., E. B. Zeleke, and S. L. Abebe. 2021. “Water leakage detection and localization using hydraulic modeling and classification.” J. Hydroinf. 23 (4): 782–794. https://doi.org/10.2166/hydro.2021.164.
Moser, G., S. German Paal, and I. F. C. Smith. 2018. “Leak detection of water supply networks using error-domain model falsification.” J. Comput. Civ. Eng. 32 (2): 04017077. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000729.
Pérez-Pérez, E. J., F. R. López-Estrada, G. Valencia-Palomo, L. Torres, V. Puig, and J. D. Mina-Antonio. 2021. “Leak diagnosis in pipelines using a combined artificial neural network approach.” Control Eng. Pract. 107 (Feb): 104677. https://doi.org/10.1016/j.conengprac.2020.104677.
Ponce, M. V. C., L. E. G. Castañón, and V. P. Cayuela. 2014. “Model-based leak detection and location in water distribution networks considering an extended-horizon analysis of pressure sensitivities.” J. Hydroinf. 16 (3): 649–670. https://doi.org/10.2166/hydro.2013.019.
Rajeswaran, A., N. Sridharakumar, and S. Narasimhan. 2018. “A graph partitioning algorithm for leak detection in water distribution networks.” Comput. Chem. Eng. 108 (Jan): 11–23. https://doi.org/10.1016/j.compchemeng.2017.08.007.
Rhodin, S. L., and E. Kvist. 2019. A comparative study between MLP and CNN for noise reduction on images: The impact of different input dataset sizes and the impact of different types of noise on performance. Stockholm, Sweden: KTH Royal Institute of Technology.
Santos-Ruiz, I., J. Blesa, V. Puig, and F. R. López-Estrada. 2020. “Leak localization in water distribution networks using classifiers with cosenoidal features.” IFAC-Pap. Online 53 (2): 16697–16702. https://doi.org/10.1016/j.ifacol.2020.12.1113.
Shukla, H., and K. Piratla. 2020. “Leakage detection in water pipelines using supervised classification of acceleration signals.” Autom. Constr. 117 (Sep): 103256. https://doi.org/10.1016/j.autcon.2020.103256.
Soldevila, A., J. Blesa, S. Tornil-Sin, E. Duviella, R. M. Fernandez-Canti, and V. Puig. 2016. “Leak localization in water distribution networks using a mixed model-based/data-driven approach.” Control Eng. Pract. 55 (Oct): 162–173. https://doi.org/10.1016/j.conengprac.2016.07.006.
Soldevila, A., R. M. Fernandez-Canti, J. Blesa, S. Tornil-Sin, and V. Puig. 2017. “Leak localization in water distribution networks using Bayesian classifiers.” J. Process Control 55 (Jul): 1–9. https://doi.org/10.1016/j.jprocont.2017.03.015.
Steffelbauer, D. B., and D. Fuchs-Hanusch. 2016. “Efficient sensor placement for leak localization considering uncertainties.” Water Resour. Manage. 30 (14): 5517–5533. https://doi.org/10.1007/s11269-016-1504-6.
Vrachimis, S. G., D. G. Eliades, R. Taormina, A. Ostfeld, Z. Kapelan, S. Liu, M. Kyriakou, P. Pavlou, M. Qiu, and M. M. Polycarpou. 2020. “Dataset of BattLeDIM: Battle of the leakage detection and isolation methods.” Zenodo. Accessed September 7, 2020. https://doi.org/10.5281/zenodo.4017659.
Wu, Y., and S. Liu. 2017. “A review of data-driven approaches for burst detection in water distribution systems.” Urban Water J. 14 (9): 972–983. https://doi.org/10.1080/1573062X.2017.1279191.
Wu, Z. Y., P. Sage, and D. Turtle. 2010. “Pressure-dependent leak detection model and its application to a district water system.” J. Water Resour. Plann. Manage. 136 (1): 116–128. https://doi.org/10.1061/(ASCE)0733-9496(2010)136:1(116).
Yu, J., L. Zhang, J. Chen, Y. Xiao, D. Hou, P. Huang, G. Zhang, and H. Zhang. 2021. “An integrated bottom-up approach for leak detection in water distribution networks based on assessing parameters of water balance model.” Water 13 (6): 867. https://doi.org/10.3390/w13060867.
Zaman, D., M. K. Tiwari, A. K. Gupta, and D. Sen. 2020. “A review of leakage detection strategies for pressurised pipeline in steady-state.” Eng. Fail. Anal. 109 (Jan): 104264. https://doi.org/10.1016/j.engfailanal.2019.104264.
Zhang, Q., Z. Y. Wu, M. Zhao, J. Qi, Y. Huang, and H. Zhao. 2016. “Leakage zone identification in large-scale water distribution systems using multiclass support vector machines.” J. Water Resour. Plann. Manage. 142 (11): 1–15. https://doi.org/10.1061/(ASCE)WR.1943-5452.0000661.
Zhou, M., Z. Pan, Y. Liu, Q. Zhang, Y. Cai, and H. Pan. 2019a. “Leak detection and location based on ISLMD and CNN in a pipeline.” IEEE Access 7: 30457–30464. https://doi.org/10.1109/ACCESS.2019.2902711.
Zhou, X., Z. Tang, W. Xu, F. Meng, X. Chu, K. Xin, and G. Fu. 2019b. “Deep learning identifies accurate burst locations in water distribution networks.” Water Res. 166 (Dec): 115058. https://doi.org/10.1016/j.watres.2019.115058.
Information & Authors
Information
Published In
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Nov 18, 2022
Accepted: Mar 23, 2023
Published online: May 24, 2023
Published in print: Aug 1, 2023
Discussion open until: Oct 24, 2023
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Computer programming
- Computing in civil engineering
- Continuum mechanics
- Dynamics (solid mechanics)
- Engineering fundamentals
- Engineering mechanics
- Environmental engineering
- Hydraulic models
- Infrastructure
- Models (by type)
- Pipe leakage
- Pipeline management
- Pipeline systems
- Pipelines
- Pollution
- Pressure (type)
- Solid mechanics
- Water and water resources
- Water leakage and water loss
- Water management
- Water pipelines
- Water pollution
- Water pressure
- Water supply
- Water supply systems
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.