Article
Engineering, Multidisciplinary
Berge Djebedjian, Hossam A. A. Abdel-Gawad, Riham M. Ezzeldin
Summary: Numerous metaheuristic optimization algorithms have been used for optimal design of water distribution networks, each showing different characteristics. New performance metrics have been proposed to evaluate the effectiveness of these algorithms, with the Fittest individual referenced Differential Evolution algorithm found to be the best.
AIN SHAMS ENGINEERING JOURNAL
(2021)
Article
Engineering, Environmental
Yujue Zhou, Jie Jiang, Kai Qian, Yulong Ding, Shuang-Hua Yang, Ligang He
Summary: Water distribution networks are crucial infrastructure, and water contamination incidents pose threats to public health. Various methods and deep learning models have been employed for contamination source identification. This paper proposes a solution for cross-network CSI based on graph convolutional networks, showing comparable accuracy even when trained on a different WDN.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2021)
Article
Environmental Sciences
Zilin Li, Chi Zhang, Haixing Liu, Chao Zhang, Mengke Zhao, Qiang Gong, Guangtao Fu
Summary: This study presents a new stacking ensemble model that uses multiple water quality parameters for contamination event detection. The proposed method outperforms an artificial neural network (ANN) benchmark method in terms of detection accuracy. The results demonstrate the great potential of the stacking method for detecting contamination events in water distribution systems.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Automation & Control Systems
Stelios G. Vrachimis, Stelios Timotheou, Demetrios G. Eliades, Marios M. Polycarpou
Summary: This study proposes a model-based methodology for leakage detection in water distribution systems, utilizing pressure and flow measurements to refine possible leak locations and retaining only those that can be explained by the interval model and available measurements from multiple time-steps.
CONTROL ENGINEERING PRACTICE
(2021)
Article
Chemistry, Analytical
Luka Grbcic, Lado Kranjcevic, Sinisa Druzeta
Summary: This paper introduces a novel methodology for solving water distribution network contamination events, using a combination of machine learning and optimization algorithms to successfully determine the source and timing of contamination. Both algorithmic frameworks perform well, with the second framework showing exceptional efficiency on networks with fuzzy sensor measurements.
Article
Environmental Sciences
Ali Fares, I. A. Tijani, Zhang Rui, Tarek Zayed
Summary: This study developed a sophisticated system for leak detection in water distribution networks (WDNs) using acoustic devices and machine learning. After conducting a two-year study on real WDNs in Hong Kong, different machine learning algorithms were used to develop inspection models for in-service and buried WDNs based on acoustic emissions acquired using wireless noise loggers. The results demonstrated the promising application of noise loggers and machine learning for leak detection in real WDNs.
ENVIRONMENTAL TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Antonio G. Spampinato, Rocco A. Scollo, Vincenzo Cutello, Mario Pavone
Summary: Community detection, an important research topic in Complex Network Analysis, plays a significant role in interpreting and understanding various systems in neuroscience, biology, social science, and economy. This paper introduces an immune optimization algorithm (opt-IA) for detecting community structures, aiming to maximize the modularity of the identified communities. Compared with 20 heuristics and metaheuristics, opt-IA demonstrates superior performance while being comparable to the Hyper-Heuristic method. The results confirm that opt-IA, despite relying on a purely random process, is reliable and efficient.
Article
Engineering, Civil
Mashor Housh, Alaa Jamal
Summary: Simulation and optimization of water distribution networks have long been a focus of research, with different formulations of heads-flows equations presenting varying degrees of dimensionality, cost, and accuracy. This study introduces a novel approach using matrix completion to construct a reduced-size nonlinear system that ensures conservation of mass and energy. The method demonstrates improved scalability, accuracy, and performance in simulation and optimization scenarios.
WATER RESOURCES MANAGEMENT
(2022)
Article
Environmental Sciences
I. A. Tijani, S. Abdelmageed, A. Fares, K. H. Fan, Z. Y. Hu, T. Zayed
Summary: This study developed machine learning-based leak detection models for real water distribution networks by recording acoustic signals and extracting features from the signals. The models developed using features extracted from de-noised signals showed better classification accuracy compared to models developed using features from raw signals.
SCIENCE OF THE TOTAL ENVIRONMENT
(2022)
Article
Computer Science, Information Systems
En-Hau Yeh, Phone Lin, Ming-Wey Huang
Summary: This article proposes an anomaly detection framework based on population distribution, using mobile network log data to monitor real-time population mobility patterns and identify critical indicators for sudden events. The framework shows a high practicality in actual situations, as demonstrated by the experiments conducted during the 2018 Hualien Earthquake in Taiwan.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Engineering, Multidisciplinary
Yu Shao, Jia Liu, Huaqi Yao, Tuqiao Zhang, Iran Lima E. Neto, Tingchao Yu, Shipeng Chu
Summary: This study presents a novel methodology that combines an improved hybrid community detection algorithm and combinatorial optimization process for partitioning water distribution networks into district metered areas (DMAs). The methodology utilizes different optimization techniques in the node clustering and partition dividing phases, resulting in more balanced water demand distribution and faster optimal solutions.
ENGINEERING OPTIMIZATION
(2022)
Article
Environmental Sciences
M. C. Cunha, R. Magini, J. Marques
Summary: This paper presents a statistical methodology for generating scenarios to solve the robust design optimization problem in water distribution networks. The methodology involves descriptive analytics of historical data, stratified sampling to generate a large number of snapshots, and reducing the number of snapshots to generate peak demand scenarios. Two heuristic techniques are proposed to reduce the number of snapshots, and two multi-objective robust optimization models are solved.
WATER RESOURCES RESEARCH
(2023)
Article
Environmental Sciences
Malvin S. Marlim, Doosun Kang
Summary: Contamination in water distribution networks can occur anytime and anywhere, hence the importance of strategically placing water quality sensors to detect and locate potential contamination sources. A robust sensor-placement strategy with clear objectives is vital for detecting, monitoring, and localizing contamination events in WDNs. The proposed optimization approach using the particle swarm optimization algorithm significantly improved the overall fitness of sensor configurations and demonstrated stable placement behavior.
Article
Engineering, Environmental
Mohammadreza Moeini, Lina Sela, Ahmad F. Taha, Ahmed A. Abokifa
Summary: Chlorine is widely used as a disinfectant in drinking water treatment and distribution systems globally. The optimization of chlorine dosage and scheduling in the distribution network is crucial to ensure water quality. This study introduces Bayesian optimization as a novel approach to optimize water quality in water distribution networks. The performance of different Bayesian optimization methods, including different acquisition functions and covariance kernels, was comprehensively analyzed. The results highlight the importance of choosing the appropriate acquisition function for optimization performance.
Article
Environmental Sciences
Ina Vertommen, Karel van Laarhoven, Maria da Conceicao Cunha
Summary: In this research, a scenario-based robust optimization approach is proposed to consider demand uncertainty in water distribution network design, allowing designers to find a balance between costs and performance. The results show that a more robust design leads to higher design costs, and numerical optimization helps in finding better design solutions.
Article
Engineering, Environmental
Qingzhou Zhang, Feifei Zheng, Yueyi Jia, Dragan Savic, Zoran Kapelan
Summary: A new method is proposed to develop real-time foul sewer system models using water consumption data from associated water distribution systems, which can accurately simulate sewer flows and manhole water depths with high efficiency values.
Article
Biodiversity Conservation
Ivana Krtolica, Dusanka Cvijanovic, Dorde Obradovic, Maja Novkovic, Djuradj Milosevic, Dragan Savic, Mirjana Vojinovic-Miloradov, Snezana Radulovic
Summary: Eutrophication is a major driver of aquatic community structure in the Danube basin. A predictive model was developed using macrophyte data to assess water quality, with good performance in the main river channel but higher discrepancies in tributaries. 28 key water quality indicators were identified from sensitivity analysis of 64 macrophyte species, mainly consisting of eutrophic tolerant submerged or emerged species.
ECOLOGICAL INDICATORS
(2021)
Review
Engineering, Multidisciplinary
Dragan Savic
Summary: The provision of water and sanitation services faces challenges and opportunities in digital transformation. Digital technology plays a crucial role in improving the efficiency and accuracy of water resource management, but there are also risks such as cybersecurity, incorrect use, and overreliance on technology. By learning from failures in industries like autonomous vehicles and aircraft, measures can be taken to ensure the safety and reliability of digital solutions in the water sector.
Article
Multidisciplinary Sciences
Shaul Sorek, Aviva Peeters, Fany Yuval, Dragan Savic
Summary: This study develops a policy-driven quantitative decision-making strategy to address the relationship between household water, food, and energy expenditures. The study introduces the concept of a nexus holistic measure and welfare mass and validates the approach through model simulations. The findings show regional variations in WFE expenditures and trends over time.
Article
Engineering, Electrical & Electronic
Dragan Savic, Petar Milic, Borislav Mazinjanin, Petar Spalevic
Summary: This paper provides a review of principles and techniques used in public-key cryptanalysis, with a focus on the RSA algorithm. It suggests ways to defend against attacks on the RSA algorithm and retrospectively describes the results obtained during the research, including brute-force attacks, low-exponent attacks, chosen-plaintext attacks, and timing attacks.
PRZEGLAD ELEKTROTECHNICZNY
(2022)
Article
Engineering, Environmental
Hamdy Elsayed, Slobodan Djordjevic, Dragan Savic, Ioannis Tsoukalas, Christos Makropoulos
Summary: A nexus-based approach is developed to explore cooperation opportunities in transboundary river basins while considering system operation and coordination under uncertain hydrologic river regimes. The approach is applied to the Nile river basin with a focus on the Grand Ethiopian Renaissance Dam (GERD), analysing the impact of different governance positions on hydropower generation and water supply.
Article
Engineering, Civil
Zixuan Zheng, Feifei Zheng, Weiwei Bi, Jiawen Du, Huan-Feng Duan, Dragan Savic, Zoran Kapelan
Summary: This study proposes a comprehensive framework to evaluate the robustness of water quality sensor placement strategies in water distribution systems to future uncertainties. The framework considers factors such as sensor failures, demand variations, and system configuration changes, and uses an optimization approach to find the best solution.
JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT
(2022)
Article
Environmental Sciences
Yiran Ji, Feifei Zheng, Jiawen Du, Yuan Huang, Weiwei Bi, Huan-Feng Duan, Dragan Savic, Zoran Kapelan
Summary: This study proposes a novel manual grab-sampling method (MGSM) for locating contamination sources in water distribution systems. By using a dynamic and cyclical sampling strategy, this method can effectively and accurately reduce the spatial range of the contamination sources, and it is applicable to scenarios with multiple contamination sources and pipe flow direction changes. The results demonstrate a balanced trade-off between detection efficiency and sampling/testing budgets.
WATER RESOURCES RESEARCH
(2022)
Article
Environmental Sciences
Yuan Huang, Jiangjiang Zhang, Feifei Zheng, Yueyi Jia, Zoran Kapelan, Dragan Savic
Summary: This paper presents the first attempt at calibrating urban drainage models using the Bayesian-based Ensemble Smoother method. Three variants of the method are tested, and the results show that ES-ILU outperforms ES-MDA and ES in terms of both accuracy and uncertainty. The calibrated models using ES-MDA and ES-ILU methods provide better results than manually obtained solutions. The study also highlights the importance of having a minimum number of observations for accurate model calibration.
WATER RESOURCES RESEARCH
(2022)
Article
Engineering, Civil
Milos Milasinovic, Damjan Ivetic, Milan Stojkovic, Dragan Savic
Summary: Climate change, energy transition, population growth, and outdated infrastructure can cause Dam and Reservoir Systems (DRS) to operate outside of their design envelope. To assess system performance under different scenarios, Digital Twins (DT) of DRSs are necessary. This paper presents a more realistic failure scenario generator based on a causal approach, utilizing fuzzy logic reasoning to create DRS failures based on hazard severity and subsystem reliability. The proposed method was demonstrated using a case study of the Pirot DRS in Serbia, showing that occasional hazards combined with outdated infrastructure can significantly reduce DRS performance and identify hidden failure risks.
WATER RESOURCES MANAGEMENT
(2023)
Article
Green & Sustainable Science & Technology
Ivana Krtolica, Dragan Savic, Bojana Bajic, Snezana Radulovic
Summary: The ecological state of the Danube River, as the most international river basin, is a major focus in the field of ecology and environmental engineering. The concentration of orthophosphate anions is an important indicator of water quality and eutrophication. This study compares eight state-of-the-art machine learning models to predict the river's ecological state using macrophyte presence scores as input variables. The results show that support vector machines and tree-based models provide the best prediction capabilities, offering a low-cost and sustainable solution for assessing river health.
Article
Green & Sustainable Science & Technology
Mehdi Khoury, Barry Evans, Otto Chen, Albert S. Chen, Lydia Vamvakeridou-Lyroudia, Dragan A. Savic, Slobodan Djordjevic, Dimitrios Bouziotas, Christos Makropoulos, Navonil Mustafee
Summary: Understanding the circular economy for water is challenging due to the complexity of the urban water cycle and its interrelations with other factors. To address this challenge, the NextGen Serious Game was developed as an online educational tool to explore the implications of circular economy strategies in different virtual catchments. The game has been successfully used in classrooms, debate facilitation, and even as a competitive tournament for water professionals, contributing to public understanding of water issues.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Computer Science, Interdisciplinary Applications
Guoxuan Liu, Dragan Savic, Guangtao Fu
Summary: Accurate water demand forecasting is crucial for urban water management in the face of urbanization, water scarcity, and climate change. This study evaluates the impact of training data length, temporal resolution, and data uncertainty on forecasting model results using a data-centric machine learning approach. The results show that data-centric machine learning approaches have the potential to improve the accuracy of short-term water demand forecasts, even with limited training data. The Random Forest and Neural Network models outperform other models when it comes to forecasting high-temporal resolution data, and improving data quality can achieve accuracy increase comparable to model-centric machine learning approaches.
JOURNAL OF HYDROINFORMATICS
(2023)
Article
Engineering, Civil
Chloe Grison, Stef Koop, Steven Eisenreich, Jan Hofman, I-Shin Chang, Jing Wu, Dragan Savic, Kees van Leeuwen
Summary: Water scarcity and accessibility continue to be significant global challenges that require attention. This paper provides a comprehensive analysis of water-related challenges in cities, including water, wastewater, municipal solid waste, and climate change. By evaluating the performance of 200 cities, representing over 95% of the global urban population, the study identifies the existing gaps in achieving water-related Sustainable Development Goals (SDGs). Most cities are not effectively managing their water resources and face challenges in achieving targets for drinking water supply, sanitation, solid waste management, climate adaptation, and informal settlements.
WATER RESOURCES MANAGEMENT
(2023)
Article
Environmental Sciences
Natalie Stephens, Frederic Been, Dragan Savic
Summary: Wastewater-based epidemiology (WBE) is recognized as a powerful tool for detecting and monitoring SARS-CoV-2 trends. This study extended the use of WBE to explore the effectiveness of nonpharmaceutical interventions (NPIs) and compare their impact on COVID-19 hospitalizations.
