Explainable Fuzzy GNNs for Leak Detection in Water Distribution Networks

2026-01-06

arXiv.org

AI Summary

This study addresses the limited interpretability and poor engineering deployability of existing graph neural network (GNN) models for leak detection in water distribution networks. To this end, we propose FGENConv, the first fuzzy interpretable GNN model tailored for water supply networks. Built upon the GENConv architecture, our method integrates mutual information to identify critical nodes and incorporates a fuzzy logic system to generate human-understandable rule-based explanations, thereby achieving both high-accuracy leak localization and transparent decision-making. Evaluated on real-world network data, FGENConv attains Graph F1 scores of 0.889 and 0.814 for leak detection and localization, respectively—slightly lower than the original GENConv but offering spatially localized, verifiable fuzzy rules that significantly enhance model trustworthiness and practical utility in engineering applications.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Generation
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Web data generation and simulation

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.

Problem

• leak detection
• water distribution networks
• explainable AI
• graph neural networks
• fuzzy logic

Innovation

• Explainable GNN
• Fuzzy Logic
• Leak Detection
• Water Distribution Networks
• Mutual Information