Modeling in the COVID-19 Pandemic: Overcoming the Water Sector’s Data Struggles to Realize the Potential of Hydraulic Models

Tiedmann, Helena R.; Spearing, Lauryn A.; Sela, Lina; Kinney, Kerry A.; Kirisits, Mary Jo; Katz, Lynn E.; Kaminsky, Jessica; Faust, Kasey M.

doi:10.1061/(asce)wr.1943-5452.0001561

Cited by 2 publications

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is not guaranteed that these patterns include all events, and real‐world data is highly volatile. For example, a model trained on data created from past patterns can fail to estimate the pressure of a WDN during the long‐term COVID‐19 pandemic due to the unexpected sudden change in water consumption that was never found in such patterns (Campos et al., 2021; Tiedmann et al., 2022). Furthermore, the number of available patterns is seldom provided or partially accessible due to privacy‐related concerns, especially in public benchmark WDNs.…”

Section: Methodsmentioning

confidence: 99%

Graph Neural Networks for Pressure Estimation in Water Distribution Systems

Truong,

Tello,

Lazovik

et al. 2024

Water Resources Research

View full text Add to dashboard Cite

Pressure and flow estimation in water distribution networks (WDNs) allows water management companies to optimize their control operations. For many years, mathematical simulation tools have been the most common approach to reconstructing an estimate of the WDNs hydraulics. However, pure physics‐based simulations involve several challenges, for example, partially observable data, high uncertainty, and extensive manual calibration. Thus, data‐driven approaches have gained traction to overcome such limitations. In this work, we combine physics‐based modeling and graph neural networks (GNN), a data‐driven approach, to address the pressure estimation problem. Our work has two main contributions. First, a training strategy that relies on random sensor placement making our GNN‐based estimation model robust to unexpected sensor location changes. Second, a realistic evaluation protocol that considers real temporal patterns and noise injection to mimic the uncertainties intrinsic to real‐world scenarios. As a result, a new state‐of‐the‐art model, GAT with Residual Connections, for pressure estimation is available. Our model surpasses the performance of previous studies on several WDNs benchmarks, showing a reduction of absolute error of ≈40% on average.

show abstract

Section: Methodsmentioning

confidence: 99%

Graph Neural Networks for Pressure Estimation in Water Distribution Systems

Truong,

Tello,

Lazovik

et al. 2024

Water Resources Research

View full text Add to dashboard Cite

show abstract

Water-energy nexus in a desalination-based water sector: the impact of electricity load shedding programs

Salomons,

Housh,

Katz

et al. 2023

npj Clean Water

View full text Add to dashboard Cite

Reliance on water production by desalination as a solution to water scarcity is growing worldwide. High energy demands of seawater desalination raise new challenges for both water and energy management and highlight the importance of understanding the operational dependencies of the water sector on energy supplies. This study provides an in-depth analysis of the impact of the water-energy nexus in a desalination-based water sector, using Israel as a case study. Being large energy consumers, desalination plants are part of the Electricity Load Shedding Program (ELSP), which government energy regulators invoke in times of energy shortage. We focus on the interdependency between the two sectors as manifested at the time of ELSP utilization during an extreme heat wave. We show that energy shedding compensation is 6 to 14 times greater than the economic loss to the desalination plant from no water production, creating an obvious economic incentive to participate in ELSPs. However, this imbalance has a substantial negative impact on the water sector, which may compromise the level of service. Our evaluation concludes that the government authorities regulating water and energy need an official mechanism and policy for joint management strategies that can ensure economic efficiency and reduce the risk of power and water shortages during extreme events.

show abstract

Modeling in the COVID-19 Pandemic: Overcoming the Water Sector’s Data Struggles to Realize the Potential of Hydraulic Models

Cited by 2 publications

References 43 publications

Graph Neural Networks for Pressure Estimation in Water Distribution Systems

Graph Neural Networks for Pressure Estimation in Water Distribution Systems

Water-energy nexus in a desalination-based water sector: the impact of electricity load shedding programs

Contact Info

Product

Resources

About