Explainable Fuzzy GNNs for Leak Detection in Water Distribution Networks

TL;DR

This paper introduces an explainable fuzzy GNN framework for leak detection in water networks, balancing detection accuracy with interpretability through rule-based explanations, aiding practical deployment by engineers.

Contribution

It develops a fuzzy-enhanced GNN model that provides transparent, rule-based explanations for leak detection, improving interpretability over traditional black-box GNNs.

Findings

Fuzzy GNN achieves 0.889 Graph F1 score for detection.

Fuzzy GNN achieves 0.814 Graph F1 score for localization.

Provides spatially localized, rule-based explanations.

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.