Riemsdijk, Chris van (2023) DeepFlow: A deep learning pipeline for leakage detection in water distribution networks. Master's Internship Report, Computing Science.
|
Text
report_research_internship_s3997049_chris.pdf Download (1MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (131kB) |
Abstract
In the literature, many efforts have been made to detect and localize leakages in water distribution networks (WDN). Leakage detection has been done by model-based, data-based, and model-transient-based methods. Many show promising results but are limited by needing a lot of historical data or that they only work on parts of WDNs, this is mostly because the models are not topologically aware. Therefore, efforts have been made to use graph neural networks (GNN) to create topological awareness within the models. As reproducibility is important, an effort is made to create a modular pipeline based on the literature to create a playground for researchers to easily train, and evaluate different GNN architectures. Moreover, we conduct our own experiments on this modular pipeline to compare with the literature.
| Item Type: | Thesis (Master's Internship Report) |
|---|---|
| Supervisor name: | Dustegor, D. and Tello Guerrero, M.A. and Truong, H.C. |
| Degree programme: | Computing Science |
| Thesis type: | Master's Internship Report |
| Language: | English |
| Date Deposited: | 19 Jul 2023 14:14 |
| Last Modified: | 19 Jul 2023 14:14 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/30789 |
Actions (login required)
 |
View Item |