Wastewater networks are mandatory for urbanisation. Their management, including the prediction and planning of repairs and expansion operations, requires precise information on their underground components (manhole covers, equipment, nodes, and pipes). However, due to their years of service and to the increasing number of maintenance operations they may have undergone over time, the attributes and characteristics associated with the various objects constituting a network are not all available at a given time. This is partly because (i) the multiple actors that carry out repairs and extensions are not necessarily the operators who ensure the continuous functioning of the network, and (ii) the undertaken changes are not properly tracked and reported. Therefore, databases related to wastewater networks may suffer from missing data. To overcome this problem, we aim to exploit the structure of wastewater networks in the learning process of machine learning approaches, using topology and the relationship between components, to complete the missing values of pipes. Our results show that Graph Convolutional Network (GCN) models yield better results than classical methods and represent a useful tool for missing data completion.
Representing and processing digital data related to underground networks, particularly sewerage networks, is increasingly becoming a priority for the managers of these networks. Indeed better representation would allow them, among others, to improve knowledge and to take the best decisions regarding these generally poorly identified infrastructures. The heterogeneity of data and the multiplicity of data models representing sewerage networks, often specific to each operator, as well as the imperfections associated with both the available data and those collected from different sources, generate complexity in terms of on-the-field interventions efficiency. They also highlight the need for aggregation (unification), control and analysis. The main objective of our work is to merge multisource data to obtain more precise and complete digital maps of sewerage networks. In this paper, we propose a generic data modelling for data fusion purposes taking into consideration the uncertainty aspects related to the collected data by allowing a confidence value for each data source and for each single data provided by a source.
Hydraulic simulation represents a powerful tool for studying wastewater networks. In order to achieve this target, hydraulic software require a set of parameters such as pipe slopes, roughness, diameters, etc. However, these pieces of information are rarely known for each and every pipe. Moreover, underground networks are frequently expanded, repaired and improved and these changes are not always reported in databases. The task of completing the required data represents the most time-consuming part of model implementation. In this context, we present algorithms that complete missing data required by hydraulic software. We automated this data insertion and transformation in SWMM© format to make it quicker and easier for the user. This automated solution was compared with manually estimated inputs. The simulation results show a coherent hydraulic behaviour.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.