The impact of sensor placement on graph-neural-network-based leakage detection

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: van Gemert, J. J. H., Breschi, V., Yntema, D. R., Keesman, K. J., Lazar, M.
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917361099997184
author van Gemert, J. J. H.
Breschi, V.
Yntema, D. R.
Keesman, K. J.
Lazar, M.
author_facet van Gemert, J. J. H.
Breschi, V.
Yntema, D. R.
Keesman, K. J.
Lazar, M.
contents Sensor placement for leakage detection in water distribution networks is an important and practical challenge for water utilities. Recent work has shown that graph neural networks can estimate and predict pressures and detect leaks, but their performance strongly depends on the available sensor measurements and configurations. In this paper, we investigate how sensor placement influences the performance of GNN-based leakage detection. We propose a novel PageRank-Centrality-based sensor placement method and demonstrate that it substantially impacts reconstruction, prediction, and leakage detection on the EPANET Net1.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24076
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The impact of sensor placement on graph-neural-network-based leakage detection
van Gemert, J. J. H.
Breschi, V.
Yntema, D. R.
Keesman, K. J.
Lazar, M.
Machine Learning
Systems and Control
Sensor placement for leakage detection in water distribution networks is an important and practical challenge for water utilities. Recent work has shown that graph neural networks can estimate and predict pressures and detect leaks, but their performance strongly depends on the available sensor measurements and configurations. In this paper, we investigate how sensor placement influences the performance of GNN-based leakage detection. We propose a novel PageRank-Centrality-based sensor placement method and demonstrate that it substantially impacts reconstruction, prediction, and leakage detection on the EPANET Net1.
title The impact of sensor placement on graph-neural-network-based leakage detection
topic Machine Learning
Systems and Control
url https://arxiv.org/abs/2603.24076