A Hybrid Data-Driven-Agent-Based Modelling Framework for Water Distribution Systems Contamination Response during COVID-19

Abstract

Contamination events in water distribution systems (WDSs) are highly dangerous events in very vulnerable infrastructure where a quick response by water utility managers is indispensable. Various studies have explored methods to respond to water events and a variety of models have been developed to simulate the consequences and the reactions of all stakeholders involved. This study proposes a novel contamination response and recovery methodology using machine learning and knowledge of the topology and hydraulics of a water network inside of an agent-based model (ABM). An artificial neural network (ANN) is trained to predict the possible source of the contamination in the network, and the knowledge of the WDS and the possible flow directions throughout a demand pattern is utilized to verify that prediction. The utility manager agent can place mobile sensor equipment to trace the contamination spread after identifying the source to identify endangered and safe places in the water network and communicate that information to the consumer agents through water advisories. The contamination status of the network is continuously updated, and the consumers reaction and decision making are determined by a fuzzy logic system considering their social background, recent stress factors based on findings throughout the COVID-19 pandemic and their location in the network. The results indicate that the ANN-based support tool, paired with knowledge of the network, provides a promising support tool for utility managers to identify the source of a possible water event. The optimization of the ANN and the methodology led to accuracies up to 80%, depending on the number of sensors and the prediction types. Furthermore, the specified water advisories according to the mobile sensor placement provide the consumer agents with information on the contamination spread and urges them to seek for help or support less.

Contamination event diagnosis in drinking water networks: A review

“…Previous studies have listed a number of response actions that can be used during emergency management situations in contaminated WDS. These include: water network partitioning for the creation of isolated network sections (Ciaponi et al, 2018(Ciaponi et al, , 2019, pipe valve closure to change the network topology and isolate contaminated areas (Hu et al, 2022;Palleti et al, 2018), flushing water from hydrants to remove contaminated water from the network (Moghaddam et al, 2022(Moghaddam et al, , 2020Fasaee et al, 2020;Hu et al, 2020b), warning consumers to change water use (Shafiee & Zechman, 2013;Kadinski et al, 2022), filtration of water (Cossali et al, 2016;Montenegro-Ayo et al, 2020;Silvestry-Rodriguez et al, 2007), boosting disinfection (Parks & VanBriesen, 2009;Karamouz et al, 2022;Van Bel et al, 2019;Helbling & VanBriesen, 2009), and slug-feed disinfection (Qiu et al, 2021). A combination of the aforementioned strategies can be applied to have a more effective response strategy.…”

“…); Maximization of the flushed contamination mass by the hydrant set, using a function that calculates the contaminant mass that exits the network from hydrant flushing locations (Fasaee et al, 2020). A notable approach uses the objective to maximize the number of protected consumers when the control action is warning the consumers through "warning tours" about how to use water safely before they are exposed to the contaminant (Shafiee & Berglund, 2016;Kadinski et al, 2022).…”

Adaptive Learning in Agent-Based Models: An Approach for Analyzing Human Behavior in Pandemic Crowding

“…Furthermore, Kadinski et al [55] employed machine learning in an agent-based model to propose a response and recovery approach for contamination events in water distribution systems. Kadinski and Ostfeld [56] also proposed an agent-based model coupled to a hydraulic simulation where the decision-making of the individual agents is based on a fuzzy logic system reacting to a contamination event in a water network.…”

Reliable and Efficient Model for Water Quality Prediction and Forecasting

“…Their study emphasized the importance of considering historical data and dynamic patterns in water quality assessment. Kadinski, L. [16] proposed a data-driven approach to identify contamination sources in water distribution systems. By integrating machine learning and network analysis, their research contributed to the early detection and management of waterborne risks.…”