Explainable Fuzzy GNNs for Leak Detection in Water Distribution Networks
Preprint
Abstract
Timely leak detection in water distribution networks is critical for conserving resources and maintaining operational efficiency. Although Graph Neural Networks (GNNs) excel at capturing spatial-temporal dependencies in sensor data, their black-box nature and the limited work on graph-based explainable models for water networks hinder practical adoption. We propose an explainable GNN framework that integrates mutual information to identify critical network regions and fuzzy logic to provide clear, rule-based explanations for node classification tasks. After benchmarking several GNN architectures, we selected the generalized graph convolution network (GENConv) for its superior performance and developed a fuzzy-enhanced variant that offers intuitive explanations for classified leak locations. Our fuzzy graph neural network (FGENConv) achieved Graph F1 scores of 0.889 for detection and 0.814 for localization, slightly below the crisp GENConv 0.938 and 0.858, respectively. Yet it compensates by providing spatially localized, fuzzy rule-based explanations. By striking the right balance between precision and explainability, the proposed fuzzy network could enable hydraulic engineers to validate predicted leak locations, conserve human resources, and optimize maintenance strategies. The code is available at github.com/pasqualedem/GNNLeakDetection.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Contrastive learning method for leak detection in water distribution networksnpj Clean Water, 2024
- Digital twin assisted decision support system for quality regulation and leak localization task in large-scale water distribution networksDigital Chemical Engineering, 2023
- Rewards, risks and responsible deployment of artificial intelligence in water systemsNature Water, 2023
- Leak Detection Methods in Water Distribution Networks: A Comparative Survey on Artificial Intelligence ApplicationsJournal of Pipeline Systems Engineering and Practice, 2022
- Data-driven application of MEMS-based accelerometers for leak detection in water distribution networksScience of The Total Environment, 2022
- Artificial intelligence in the water domain: Opportunities for responsible useScience of The Total Environment, 2021
- Leak localization in water distribution networks using Bayesian classifiersJournal of Process Control, 2017
- WML: Wireless Sensor Network based Machine Learning for Leakage Detection and Size EstimationProcedia Computer Science, 2015
- Interpretability of linguistic fuzzy rule-based systems: An overview of interpretability measuresInformation Sciences, 2011
- Pressure-Dependent Leak Detection Model and Its Application to a District Water SystemJournal of Water Resources Planning and Management, 2010