Water distribution networks play a crucial role in delivering safe water to communities. However, their extensive reach and complex structure make them susceptible to contamination. The development of efficient contamination warning systems (CWSs) can enable the monitoring and control of abnormal events. In an efficient CWS, several key aspects must be addressed: identifying potential contaminations that can occur, determining the most effective water parameters to monitor, and defining where these parameters can be strategically monitored. In the present study, literature articles will be analyzed to explore different parameters for detecting anomalies, assess the information they provide, and highlight the benefits of combining various parameters. Moreover, attention will be given to the definition of sensor placement, emphasizing the lack of attention in the literature for defining sensors’ detection thresholds. Finally, the study underscores that ensuring human safety requires not only prompt intrusion detection but also the implementation of corrective and preventive actions capable of mitigating contaminant spread through WDNs.
Water distribution networks (WDNs) are characterized by complex challenges in management and optimization, especially in ensuring efficiency, reducing losses, and maintaining infrastructure performances. The recent advancements in Artificial Intelligence (AI) techniques based on Large Language Models, particularly ChatGPT 4.0 (a chatbot based on a generative pre-trained model), offer potential solutions to streamline these processes. This study investigates the ability of ChatGPT to perform the clustering phase of WDN partitioning, a critical step for dividing large networks into manageable clusters. Using a real Italian network as a case study, ChatGPT was prompted to apply several clustering algorithms, including k-means, spectral, and hierarchical clustering. The results show that ChatGPT uniquely adds value by automating the entire workflow of WDN clustering—from reading input files and running algorithms to calculating performance indices and generating reports. This makes advanced water network partitioning accessible to users without programming or hydraulic modeling expertise. The study highlights ChatGPT’s role as a complementary tool: it accelerates repetitive tasks, supports decision-making with interpretable outputs, and lowers the entry barrier for utilities and practitioners. These findings demonstrate the practical potential of integrating large language models into water management, where they can democratize specialized methodologies and facilitate wider adoption of WDN managing strategies.
Water distribution networks (WDNs) are critical infrastructure yet vulnerable to contamination, thereby threatening public health. Rapid contaminant detection through sensor systems is essential for water safety. This study compares topological and optimization-based methods for sensor placement under intentional and accidental contamination scenarios triggered by low-pressure events. A novel approach is introduced to model pipe break events that generate low-pressure zones, creating pathways for contamination. Unlike traditional models, this method dynamically estimates contaminant intrusion volume based on the available node pressure. The study reveals that while optimization-based sensor placement yields better outcomes than the topological approach, the performance gap narrows as the number of sensors increases or when the system is tested against scenarios different from those used for optimization. The findings highlight a major issue in sensor detection when water quality is considered. For E. coli contamination in a chlorinated system, two conclusions emerge: rapid inactivation of E. coli makes it an unreliable indicator, even with optimized sensors, and sensor type and detection thresholds significantly affect performance, requiring careful assessment before implementation. This study provides a framework for evaluating sensor systems in WDNs, emphasizing tailored strategies that consider hydraulic conditions and water quality dynamics to improve contamination detection and public safety.
Water-distribution networks (WDNs) are vital infrastructure that are exposed to the risk of contamination. Several factors contribute to this risk, including insufficient pressure, contamination in water storage tanks and more. Sensor systems are crucial for detecting contaminations promptly. Traditional optimization methods to define sensor locations often require resource-intensive network modeling, posing challenges for water utilities. This study applies a topological approach using betweenness centrality to address sensor placement. Various weights based on the physical structure of the network are tested. Results highlight the effectiveness of weighted topological approaches in minimizing contamination’s public health impact, with the advantage of low computational costs inherent in graph-based network representations.
SWANP-AI (Smart Water Network Partitioning with Artificial Intelligence) is a web application with AI natively embedded in its core engines for automated Water Network Partitioning (WNP) of water distribution networks. It is presented as the web-based evolution of SWANP 4.0, whose computational routines have already been tested in operational and research applications. The paper clarifies the full development chain of the platform, from graph-based grouping of candidate District Metered Areas/pressure management Areas (DMA/PMA) to multi-objective boundary pipe optimization and operational decision support. The methodology combines spectral and multilevel k-way partitioning for district generation, NSGA-II for cost–resilience boundary selection, hydraulic simulation through EPANET/WNTR, and AI-supported modules for solution interpretation, sensor placement, natural language editing, and Bayesian leak localization. The application to a real water distribution network shows that SWANP-AI can transform natural language engineering requests into formal optimization tasks, identify hydraulically meaningful candidate interventions, and select balanced solutions through Utopia point analysis, thus reducing manual trial-and-error in DMA/PMA design. The main contribution is a structural generative AI workflow that supports engineers not only in analyzing a network as it is, but also in designing how the network should be partitioned and operated.
Urbanization and climate change affect subsurface thermal conditions, yet the impact of contrasting urban thermal environments-urban heat islands (UHIs) versus cool islands (CIs)-on drinking water quality remains poorly characterized. This study compared water temperature and quality in two thermally distinct districts in Montréal, Canada, through fifteen sampling events (June-November 2024) spanning spring, summer, and fall. Event-specific hydraulic modeling was coupled with field measurements of temperature, free chlorine, microbial indicators (ATP, total cell counts), and disinfection by-products (DBPs) to estimate water age and chlorine consumption. The CI exhibited greater thermal buffering, with 26% of warm-season samples cooling >3°C versus 3% in the UHI. However, free chlorine frequently fell below the 0.2 mg/L threshold in both districts (40% CI, 45% UHI in summer). Residuals below 0.2 mg/L systematically coincided with elevated microbial indicators, confirming this threshold as critical for microbial control. Chlorine consumption was higher in the UHI during warm periods at short-to-moderate residence times, reflecting thermal amplification of decay. DBPs exhibited strong seasonal patterns (summer > spring > fall) but no systematic district separation. Multivariate analysis confirmed that disinfectant residuals and residence time dominate microbial and DBP behavior, with temperature acting as a secondary amplifying factor. These results demonstrate that urban thermal environments interact with hydraulic and operational factors to influence water quality, with entry-point management remaining critical regardless of local thermal conditions. This study underscores the need for integrated field-model approaches to support climate-resilient drinking water management under intensifying urbanization and warming.