https://doi.org/10.1140/epjs/s11734-025-01517-y
Regular Article
Reducing adversarial sensor data predictions in water leak management by applying the advection–diffusion and ensemble models
Department of Computer Applications, National Institute of Technology Tiruchirappalli, 620015, Tiruchirappalli, Tamilnadu, India
Received:
9
October
2024
Accepted:
6
February
2025
Published online:
13
February
2025
In distribution systems, efficient water leak management is essential, especially in climate-variable environments, to minimize false alarms brought on by noisy sensor data. By combining ensemble learning methods with an Advection–Diffusion Model, this study offers a novel strategy for enhanced leak detection. Adaptive Boosting, a Stacked Meta-Model, and Bagged Support Vector Machines (SVM) are among the ensemble techniques used to precisely locate and identify leaks by utilizing a variety of features from sensor data. This technique improves leak detection accuracy and robustness by combining several machine learning algorithms, even in dynamic environmental conditions. The difficulties caused by sensor noise are addressed by combining these ensemble approaches with fluid dynamics models, which enhances leak detection efficiency and reduces false alarms. The findings show a notable improvement in leak localization and detection, providing a flexible and affordable way to manage water distribution networks in the face of climate-related variability.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to EDP Sciences, Springer-Verlag GmbH Germany, part of Springer Nature 2025
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
