Water distribution networks (WDNs) are critical contributors to the social welfare, economic growth, and public health in cities. Under the uncertainties that are introduced owing to climate change, urban development, aging components, and interdependent infrastructure, the WDN performance must be evaluated using continuously innovative methods and data acquisition. Quantitative resilience assessments provide useful information for WDN operators and planners, enabling support systems that can withstand disasters, recover quickly from outages, and adapt to uncertain environments. This study reviews contemporary approaches for quantifying the resilience of WDNs. 1508 journal articles published from 1950 to 2018 are identified under systematic review guidelines. 137 references that focus on the quantitative resilience methods of WDN are classified as surrogate measures, simulation methods, network theory approaches, and fault detection and isolation approaches. This study identifies the resilience capability of the WDNs and describes the related terms of absorptive, restorative, and adaptive capabilities. It also discusses the metrics, research progresses, and limitations associated with each method. Finally, this study indicates the challenges associated with the quantification of WDNs that should be overcome for achieving improved resilience assessments in the future.

Water distribution networks (WDNs) represent a class of critical infrastructure networks. When a disaster occurs, component failures in a WDN may trigger system failures that result in larger-scale reactions. The aim of the paper is to evaluate the evolution of system reliability and failure propagation time for a WDN experiencing cascading failures, and find the critical pipes which may reduce system reliability dramatically. Multiple factors are considered in the method such as network topology, the balance of water supply and demand, demand multiplier, and pipe break isolation. The pipe-based attack with multiple failure scenarios is simulated in the paper. A case WDN is used to illustrate the method. The results show that the lowest capacity gets stronger when a WDN is short of supply, becoming the dominant factor that decides the evolution of system reliability and failure propagation time. The valve ratio (VR) and system reliability present a flattened S curve relationship, and there are two turning points in VR. The critical pipes can be identified. With the fixed 5% valves, a WDN can improve system reliability and resist cascading failures effectively. The findings provide insights into the system reliability and failure propagation time for WDNs experiencing cascading failures. It is proven to be useful in future studies focused on the operation and management of water services.

Predicting water demand helps decision-makers allocate regional water resources efficiently, thereby preventing water waste and shortage. The aim of this study is to predict water demand in the Beijing–Tianjin–Hebei region of North China. The explanatory variables associated with economy, community, water use, and resource availability were identified. Eleven statistical and machine learning models were built, which used data covering the 2004–2019 period. Interpolation and extrapolation scenarios were conducted to find the most suitable predictive model. The results suggest that the gradient boosting decision tree (GBDT) model demonstrates the best prediction performance in the two scenarios. The model was further tested for three other regions in China, and its robustness was validated. The water demand in 2020–2021 was provided. The results show that the identified explanatory variables were effective in water demand prediction. The machine learning models outperformed the statistical models, with the ensemble models being superior to the single predictor models. The best predictive model can also be applied to other regions to help forecast water demand to ensure sustainable water resource management.

The construction industry is fraught with danger. The investigation of the causes of occupational accidents receives considerable attention. The purpose of this research is to determine the hierarchical relationship and critical combination of the fatal causes of accidents on construction sites. The framework for fatal cause attribute was established. Machine learning technologies were developed to predict the different types of accidents. Using feature importance, the hierarchical relationship of fatal causes was extracted. An iterative analysis algorithm was created to quantify the cause combinations. The F1 prediction score was 92.93%. The results revealed that combinations existed in fatal causes analysis, even if they were hierarchical. Furthermore, this study made recommendations for improving safety management and preventing occupational accidents. The findings of this study guide construction participants in providing early warning signs of fatal and unsafe factors, ultimately assisting in the prevention of fatalities.