An Interpretable Stacked Ensemble Model for Classifying Abnormal Non-Revenue Water

1. Farley M. Non-revenue water – international best practice for assessment, monitoring and control. 2003.
2. Hirner W, Lambert AO. Losses from water supply systems: standard terminology and recommended performance measures. London: International Water Association; 2000.
3. Al-Washali TM. Water loss assessment in distribution networks: methods, applications and implications in intermittent supply. 1st ed. CRC Press; 2021. doi:10.1201/9781003167938
4. Mutikanga H, Sharma S, Vairavamoorthy K. Investigating water meter performance in developing countries: a case study of Kampala, Uganda. Water SA.2011;37(4):567–574. doi:10.4314/wsa.v37i4.18
5. Blesa J, Pérez R. Modelling uncertainty for leak localization in water networks. IFAC-PapersOnLine. 2018;51(24):730–735. doi:10.1016/j.ifacol.2018.09.656
6. Chen T, Guestrin C. XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discoveryand Data Mining. 2016. p. 785–794. doi:10.1145/2939672.2939785
7. Elkharbotly MR, Seddik M, Khalifa A. Toward sustainable water: prediction of non-revenue water via artificial neural network and multiple linear regression modelling approach in Egypt. Ain Shams Eng J. 2022;13(5):101673. doi:10.1016/j.asej.2021.101673
8. Farah B, Awad M, Rutrot A. Prediction for non-revenue and demand of urban water using hybrid models of neural networks and genetic algorithms. 2022;(21).
9. Kızılöz B. Prediction of non-revenue water ratio in water distribution systems. Sigma J Eng Nat Sci. 2024:653–666. doi:10.14744/sigma.2024.00061
10. Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE.2015;10(3):e0118432. doi:10.1371/journal.pone.0118432
11. Lundberg S, Lee SI. A unified approach to interpreting model predictions. arXiv:1705.07874. 2017. doi:10.48550/arXiv.1705.07874 [12].
12. Water Services Regulatory Board (WASREB). Impact 18: water services sector performance report. 2026. https://wasreb.go.ke/
13. Kingdom B, Liemberger R, Marin P. The challenge of reducing non-revenue water (NRW) in developing countries: how the private sector can help. Washington, DC: World Bank; 2006.
14. Water Services Regulatory Board (WASREB). Impact 17. 2025.
15. Hastie T, Tibshirani R, Friedman JH. The elements of statistical learning: data mining, inference, and prediction. 2nd ed. Springer; 2009. doi:10.1007/978-0-387-84858-7
16. Mwitirehe J, Kipruto CW, Ruranga C. Analyzing non-revenue water dynamics in Rwanda: leveraging machine learning predictive modeling for comprehensive insights and mitigation strategies. Water Pract Technol. 2024;19(6):2376–2398. doi:10.2166/wpt.2024.145
17. Berlotti M, Di Grande S, Cavalieri S, Gueli R. Detection and prediction of leakages in water distribution networks. In: Proceedings of the 12th International Conference on Data Science, Technology and Applications. 2023. p. 436–443. doi:10.5220/0012122000003541
18. Muriithi PK. A machine learning model to predict non-revenue water with severely unbalanced classes [master’s thesis]. Nairobi: Strathmore University; 2022.
19. Warad AAM, Wassif K, Darwish NR. An ensemble learning model for forecasting water-pipe leakage. Sci Rep. 2024;14:10683. doi:10.1038/s41598-024-60840-x