Coupling Machine Learning and Agent-Based Modeling to Characterize Contamination Sources in Water Distribution Systems for Changing Demand Regimes

Water distribution systems (WDSs) deliver clean, safe drinking water to consumers, providing an essential service to constituents. WDSs are increasingly at risk of contamination due to aging infrastructure and intentional acts that are possible through cyber-physical vulnerabilities. Identifying the source of a contamination event is challenging due to limited system-wide water quality monitoring and non-uniqueness present in solving inverse problems to identify source characteristics. In addition, changes in the expected demand patterns that are caused by, for example, social distancing during a pandemic, adoption of water conservation behaviors, or use of decentralized water sources can change the anticipated propagation of contaminant plumes in a network. This research develops a computational framework to characterize contamination sources using machine learning (ML) techniques and simulate water demands and human exposure to a contaminant using agent-based modeling (ABM). An ABM framework is developed to simulate demand changes during the COVID-19 pandemic. The ABM simulates population movement dynamics, transmission of COVID-19 within a community, decisions to social distance, and changes in demands that occur due to social distancing decisions. The ABM is coupled with a hydraulic simulation model, which calculates flows in the network to simulate the movement of a contaminant plume in the network for several contamination event scenarios. ML algorithms are applied to determine the location of source nodes. Research results demonstrate that ML using random forests can identify source nodes based on inline and mobile sensor data. Sensitivity analysis is conducted to explore the number of mobile sensors that are needed to accurately identify the source node. Rapidly identifying contamination source nodes can increase the speed of response to a contamination event, reducing the impact to the community and increasing the resiliency of WDSs during periods of changing demands. © World Environmental and Water Resources Congress 2023.All rights reserved

An agent-based model for contamination response in water distribution systems during the COVID-19 pandemic

Contamination events in water distribution systems (WDS) are emergencies that cause public health crises and require fast response by the responsible utility manager. Various models have been developed to explore the reactions of relevant stakeholders during a contamination event, including agent-based modeling. As the COVID-19 pandemic has changed the daily habits of communities around the globe, consumer water demands have changed dramatically. In this study, an agent-based modeling framework is developed to explore social dynamics and reactions of water consumers and a utility manager to a contamination event, while considering regular and pandemic demand scenarios. Utility manager agents use graph theory algorithms to place mobile sensor equipment and divide the network in sections that are endangered of being contaminated or cleared again for water consumption. The status of respective network nodes is communicated to consumer agents in real time, and consumer agents adjust their water demands accordingly. This sociotechnological framework is presented using the overview, design, and details protocol. The results comprise comparisons of reactions and demand adjustments of consumers to a water event during normal and pandemic times, while exploring new methods to predict the fate of a contaminant plume in the WDS.

A Socio-Technological Framework for Optimizing Water Utility Strategies and Resilience to Pandemic Changes and Contamination Events

Water distribution systems are critical infrastructure that deliver high quality drinking water to its consumers. Contamination events in water distribution systems (WDS) are emergencies that can cause distress in the population and require quick response from the responsible utility manager. While regular water quality parameters are monitored at water treatment facilities, it is still a challenge to monitor water quality in the WDS itself. Various models have been developed to explore the reactions and interactions of relevant stakeholders during a contamination event including agent-based modelling. Furthermore, recent research has shown that water demands have significantly changed during the COVID-19 pandemic, and these changes can affect the operation and management of water infrastructure. In this study, an agent-based modelling framework is developed to explore social dynamics and reactions of water consumers and a utility manager during a contamination event, while considering a pandemic demand scenario. Furthermore, innovative response and recovery methods to a contamination event are explored for rehabilitating the water network after a water quality deterioration. Graph theory algorithms are used to place mobile sensor equipment for surveying the water quality in specific network parts, and the distribution system is clustered by the status of endangerment. The Bayesian Belief Network (BBN) was developed using survey data around risk perceptions and social distancing behaviour that were collected during the COVID-19 pandemic. The agent-based model (ABM) was developed using output from the BBN and water use data that were collected during the COVID-19 pandemic. The ABM is coupled with hydraulic simulation of the water infrastructure to evaluate changes in hydraulic performance. The model can be used to explore long and short-term consequences of the pandemic on water distribution systems' management, design, and operations;develop and optimize strategies of how to deal with changes in around water distribution systems due to the pandemic;and investigate how resilient water utilities can cope with additional catastrophic events such as a contamination of a water system during a global or local pandemic related shutdown. © ASCE.

Design for sustainability transformations: A deep leverage points research agenda for the (post-)pandemic context

This position paper presents a prototype research agenda for design for sustainability transformations (DfST) in the (post-)pandemic context. COVID-19 has made visible vulnerabilities, structural dysfunctions, inequalities and injustices across health, environmental, social, economic, provisional and political systems. In response to the crisis, rapid, adaptive, technological and social innovations have started to emerge across all levels of society, opening up a multiplicity of alternative futures. This is an opportune time to address long-standing and urgent sustainability challenges in ways that move beyond the ineffective and business-as-usual approaches of ecological modernism. The authors used a co-creative process to identify weak signals relevant to sustainability transformations. In alignment with the deep leverage points framework, the identified weak signals are presented under two main headings: First, social structures and institutions;and second, values, goals and worldviews. The deep leverage points form the basis of a research agenda on how DfST could contribute to sustainability transformations right now and in the longer-term. © 2021 Universidade do Vale do Rio dos Sinos. All rights reserved.

Water and Wastewater Systems and Utilities: Challenges and Opportunities during the COVID-19 Pandemic

Forum papers are thought-provoking opinion pieces or essays founded in fact, sometimes containing speculation, on a civil engineering topic of general interest and relevance to the readership of the journal. The views expressed in this Forum article do not necessarily reflect the views of ASCE or the Editorial Board of the journal.