Scalable and Robust Physics-Informed Graph Neural Networks for Water Distribution Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917927201013760 |
|---|---|
| author | Ashraf, Inaam Artelt, André Hammer, Barbara |
| author_facet | Ashraf, Inaam Artelt, André Hammer, Barbara |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12164 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Scalable and Robust Physics-Informed Graph Neural Networks for Water Distribution Systems Ashraf, Inaam Artelt, André Hammer, Barbara Neural and Evolutionary Computing Machine Learning Systems and Control 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. |
| title | Scalable and Robust Physics-Informed Graph Neural Networks for Water Distribution Systems |
| topic | Neural and Evolutionary Computing Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2502.12164 |