Emerging trends of resilient and reliable water infrastructure advocate for the development of efficient state estimation (SE) techniques in water distribution systems (WDSs). SE refers to estimating the flows and heads in the WDS at unmonitored locations based on measurements collected from limited monitoring locations. Current physics-based SE methods typically require more exhaustive than readily available information about the WDS and are computationally demanding to attain real-time SE fully. Using neural networks for SE is a promising avenue because neural networks are more adaptable to the availability of sensory data and can shift most of the computation efforts to the offline training phase. Once trained, the inference is more computationally efficient compared to the physics-based SE methods. This work proposes a graph neural network (GNN) model for SE in WDSs. Unlike traditional neural networks, GNNs are more suitable for the SE problem for two main reasons: (1) given a limited number of monitoring locations, the SE problem inherently requires a semisupervised learning method, and (2) GNNs enable learning from the graph structure of a WDS, thus providing a mechanism to incorporate the functional relationships between the monitored and unmonitored locations and incorporate the physical laws during the training process. To evaluate the performance of GNNs for SE, we tested supervised and semisupervised approaches, investigated the impact of GNN architecture choices on its performance, and examined model performance under different levels of noise in the training data. The results demonstrate that GNNs are promising for SE for their ability to learn from graph structure with a limited amount of information while exhibiting robustness to noise. This study contributes toward advancing real-time GNN-based SE in WDSs. Future research is needed to incorporate various hydraulic devices and investigate the scalability of GNNs to large-scale WDSs.

With the increasing adoption of demand management strategies and water conservation practices, domestic water consumption is projected to decline in the future. The subsequent consumer-side demand reductions are expected to result in increased residence times in water distribution networks (WDNs), and thus could have negative effects on the water quality (WQ) reaching the consumers’ taps. This study evaluates the impacts of the projected decrease in residential water demands on the deterioration of the WQ in WDNs. This deterioration will likely be most prominent in the dead-end branches at the perimeters of WDNs, where the flow is characteristically low and intermittent. The assessment of WQ deterioration in the dead-end branches requires the implementation of an accurate WQ simulation model. To this end, a new Python-based software package, WUDESIM_Py, is first introduced. The WQ simulation engine in WUDESIM_Py is based on an advection-dispersion-reaction model and accounts for the spatial distribution of water demands along dead-end pipes. WUDESIM_Py comprises various sets of functions that allow the users to set-up and conduct WQ simulations as well as obtain and visualize simulation results. A complete description of the different functions, together with examples of how these functions can be implemented in different applications, is provided. Through conducting extensive simulations of benchmark WDNs, the results revealed that widespread adoption of water conservation practices can lead to significant WQ deterioration in the dead-end branches. Additionally, the results suggested that neglecting dispersive transport and spatially aggregating demands may result in overestimating residual chlorine concentrations in the dead-end branches, which could mask the real impacts of demand reduction on WQ deterioration.

As pipelines in water distribution networks (WDNs) age and deteriorate, pipe bursts have become increasingly frequent, wasting a significant amou |