Node Pressure Prediction by Aggregating Long-Range Information DOI
Pinghua Xu, Wenhang Yu, Zhou Xu

и другие.

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 53 - 65

Опубликована: Ноя. 16, 2024

Язык: Английский

Reliability Analysis of Water Distribution System using Benchmark Table DOI

Suja S. Nair,

Meyyappan Palaniappan

Water Resources Management, Год журнала: 2025, Номер unknown

Опубликована: Фев. 26, 2025

Язык: Английский

Процитировано

0

Dynamic-demand vulnerability analysis of water networks using a two-index neural network algorithm DOI
Baowen Zhang

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 151, С. 110581 - 110581

Опубликована: Март 26, 2025

Язык: Английский

Процитировано

0

Heterogeneous graph neural networks enhance pressure estimation in water distribution networks DOI Creative Commons
Jian Wang, Liu Li, Dragan Savić

и другие.

Water Research, Год журнала: 2025, Номер 283, С. 123843 - 123843

Опубликована: Май 16, 2025

Pressure estimation is crucial for efficient operation and management of water distribution networks (WDNs). However, it often challenged by limited sensor observations. While graph neural (GNNs) have been used to improve hydraulic quality predictions WDNs, their reliance on homogeneous graphs oversimplifies the diverse roles interactions components, resulting in lower performance under dynamic system states. This research introduces a novel heterogeneous network (HGNN) framework, which models control units such as pumps valves distinct nodes while preserving through additional edge types. Experimental results using C-Town benchmark demonstrate that HGNN outperforms GNN terms accuracy, robustness, adaptability, achieving mean absolute percentage error (MAPE) 1.88 % (MAE) 1.70 m 95 masking rate. Additionally, this study shows optimal placement reduces MAE up 15 %, proposed framework achieves high computational efficiency, highlighting its effectiveness WDN analysis management. offers an advanced transferable approach pressure estimation, serving superior alternative traditional evaluation models.

Язык: Английский

Процитировано

0

Large-Scale Multipurpose Benchmark Datasets for Assessing Data-Driven Deep Learning Approaches for Water Distribution Networks DOI Creative Commons
Andrés Tello, Huy Truong, Alexander Lazovik

и другие.

Опубликована: Сен. 4, 2024

Язык: Английский

Процитировано

1

DiTEC: Digital Twin for Evolutionary Changes in Water Distribution Networks DOI Creative Commons
Viktoriya Degeler, Mostafa Hadadian Nejad Yousefi, Erkan Karabulut

и другие.

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 62 - 82

Опубликована: Окт. 25, 2024

Язык: Английский

Процитировано

0

A Full and Simplified Water Distribution Network Model Comparison of Skeletonization Results DOI Creative Commons
Brian Tugume, Mario Castro-Gama, David Ayala–Cabrera

и другие.

Опубликована: Сен. 5, 2024

Язык: Английский

Процитировано

0

Node Pressure Prediction by Aggregating Long-Range Information DOI
Pinghua Xu, Wenhang Yu, Zhou Xu

и другие.

Lecture notes in computer science, Год журнала: 2024, Номер unknown, С. 53 - 65

Опубликована: Ноя. 16, 2024

Язык: Английский

Процитировано

0