Scalable and Robust Physics-Informed Graph Neural Networks for Water Distribution Systems

TL;DR

This paper introduces a scalable, physics-informed graph neural network model for water distribution systems that improves robustness, efficiency, and scalability, aiding infrastructure planning and management.

Contribution

It presents a novel, physics-informed GNN architecture with an innovative training scheme and data normalization, enhancing performance and scalability over existing models.

Findings

Outperforms current state-of-the-art DL models on WDSs

Scales effectively to larger, more realistic systems

Increases robustness to out-of-distribution inputs

Abstract

Water distribution systems (WDSs) are an important part of critical infrastructure becoming increasingly significant in the face of climate change and urban population growth. We propose a robust and scalable surrogate deep learning (DL) model to enable efficient planning, expansion, and rehabilitation of WDSs. Our approach incorporates an improved graph neural network architecture, an adapted physics-informed algorithm, an innovative training scheme, and a physics-preserving data normalization method. Evaluation results on a number of WDSs demonstrate that our model outperforms the current state-of-the-art DL model. Moreover, our method allows us to scale the model to bigger and more realistic WDSs. Furthermore, our approach makes the model more robust to out-of-distribution input features (demands, pipe diameters). Hence, our proposed method constitutes a significant step towards bridging the simulation-to-real gap in the use of artificial intelligence for WDSs.