{"title":"Water saving and management","authors":"Wenjun Sun, Shane Allen Snyder","doi":"10.2166/aqua.2024.001","DOIUrl":"https://doi.org/10.2166/aqua.2024.001","url":null,"abstract":"","PeriodicalId":513288,"journal":{"name":"AQUA — Water Infrastructure, Ecosystems and Society","volume":"31 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140081785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Air valves and pressure vessels are among the most important protection devices used to protect the main pumping lines due to their reliability in controlling transient pressures. The proper and rational design of the water hammer protection devices ensures high efficiency in controlling the values of transient pressures. For this purpose, the genetic algorithm approach was adopted in the process of selecting the optimal parameters for both pressure vessels (size, orifice diameter) and air valve (orifice diameter of inlet and outlet, discharge coefficients of inlet and outlet) in addition to determining the type and location of the air valve. The performance of the proposed protection devices was verified by comparing three objective equations: (1) minimizing the cost of protection devices, (2) minimizing the difference between the maximum and minimum pressure, and (3) minimizing difference between the maximum and minimum pressure with a specific constraint on the budget of protection devices. The study results showed that selecting the optimal design parameters for pressure vessels and air valves helps control the cost of protection devices and transient pressure values.
{"title":"Optimal parameters of protection devices for controlling hydraulic transient using genetic algorithms","authors":"Mohammed Salah Alhwij, Wissam Nakhleh","doi":"10.2166/aqua.2024.323","DOIUrl":"https://doi.org/10.2166/aqua.2024.323","url":null,"abstract":"\u0000 \u0000 Air valves and pressure vessels are among the most important protection devices used to protect the main pumping lines due to their reliability in controlling transient pressures. The proper and rational design of the water hammer protection devices ensures high efficiency in controlling the values of transient pressures. For this purpose, the genetic algorithm approach was adopted in the process of selecting the optimal parameters for both pressure vessels (size, orifice diameter) and air valve (orifice diameter of inlet and outlet, discharge coefficients of inlet and outlet) in addition to determining the type and location of the air valve. The performance of the proposed protection devices was verified by comparing three objective equations: (1) minimizing the cost of protection devices, (2) minimizing the difference between the maximum and minimum pressure, and (3) minimizing difference between the maximum and minimum pressure with a specific constraint on the budget of protection devices. The study results showed that selecting the optimal design parameters for pressure vessels and air valves helps control the cost of protection devices and transient pressure values.","PeriodicalId":513288,"journal":{"name":"AQUA — Water Infrastructure, Ecosystems and Society","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140415167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Juliana Marçal, Junjie Shen, Blanca Antizar-Ladislao, David Butler, Jan Hofman
Water security is a multi-faceted concept that encompasses dimensions such as water quantity, quality, human health, well-being, water hazards, and governance. The evaluation of water security is an important step towards understanding and improving it, particularly in urban settings where disparities resulting from unequal distribution of population and resources are present and often evade citywide assessments. To address the diversity of the urban space, we propose a multi-level assessment approach based on downscaling the spatial dimension. Using a comprehensive indicator-based framework, we evaluate the city of Campinas in Brazil across citywide and intra-city scales. Employing the Theil index to measure inequality, the results reveal nuanced disparities less apparent at broader scales. Despite an overall favourable water security condition, spatial heterogeneity is still noticeable in the urban area of Campinas. The methodology highlights different aspects, such as vegetation cover, social green areas, and wastewater collection, which are inequitably distributed in the urban area. This integrated approach linking inequality and water security assessment, has the potential to unveil specific needs within urban areas, helping guide targeted interventions to improve water security levels for all.
{"title":"Urban water security assessment: investigating inequalities using a multi-scale approach","authors":"Juliana Marçal, Junjie Shen, Blanca Antizar-Ladislao, David Butler, Jan Hofman","doi":"10.2166/aqua.2024.307","DOIUrl":"https://doi.org/10.2166/aqua.2024.307","url":null,"abstract":"\u0000 \u0000 Water security is a multi-faceted concept that encompasses dimensions such as water quantity, quality, human health, well-being, water hazards, and governance. The evaluation of water security is an important step towards understanding and improving it, particularly in urban settings where disparities resulting from unequal distribution of population and resources are present and often evade citywide assessments. To address the diversity of the urban space, we propose a multi-level assessment approach based on downscaling the spatial dimension. Using a comprehensive indicator-based framework, we evaluate the city of Campinas in Brazil across citywide and intra-city scales. Employing the Theil index to measure inequality, the results reveal nuanced disparities less apparent at broader scales. Despite an overall favourable water security condition, spatial heterogeneity is still noticeable in the urban area of Campinas. The methodology highlights different aspects, such as vegetation cover, social green areas, and wastewater collection, which are inequitably distributed in the urban area. This integrated approach linking inequality and water security assessment, has the potential to unveil specific needs within urban areas, helping guide targeted interventions to improve water security levels for all.","PeriodicalId":513288,"journal":{"name":"AQUA — Water Infrastructure, Ecosystems and Society","volume":"2004 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140416319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Water cyber-physical systems (CPSs) have experienced anomalies from cyber-physical attacks as well as conventional physical and operational failures (e.g., pipe leaks/bursts). In this regard, rapidly distinguishing and identifying a facing failure event from other possible failure events is necessary to take rapid emergency and recovery actions and, in turn, strengthen system's resilience. This paper investigated the performance of machine learning classification models – Support Vector Machine (SVM), Random Forest (RF), and artificial neural networks (ANNs) – to differentiate and identify failure events that can occur in a water distribution network (WDN). Datasets for model features related to tank water levels, nodal pressure, and water flow of pumps and valves were produced using hydraulic model simulation (WNTR and epanetCPA tools) for C-Town WDN under pipe leaks/bursts, cyber-attacks, and physical attacks. The evaluation of accuracy, precision, recall, and F1-score for the three models in failure type identification showed the variation of their performances depending on the specific failure types and data noise levels. Based on the findings, this study discussed insights into building a framework consisting of multiple classification models, rather than relying on a single best-performing model, for the reliable classification and identification of failure types in WDNs.
水网络物理系统（CPS）曾经历过网络物理攻击以及传统物理和运行故障（如管道泄漏/爆裂）造成的异常情况。在这方面，从其他可能的故障事件中快速区分和识别所面临的故障事件是采取快速应急和恢复行动的必要条件，反过来也能增强系统的恢复能力。本文研究了机器学习分类模型--支持向量机（SVM）、随机森林（RF）和人工神经网络（ANN）--在区分和识别配水管网（WDN）中可能发生的故障事件方面的性能。利用水力模型模拟（WNTR 和 epanetCPA 工具）为 C 镇 WDN 在管道泄漏/爆裂、网络攻击和物理攻击的情况下生成了与水箱水位、节点压力以及水泵和阀门的水流量相关的模型特征数据集。对三种模型在故障类型识别中的准确度、精确度、召回率和 F1 分数进行的评估表明，它们的性能因具体故障类型和数据噪声水平而异。基于这些发现，本研究探讨了如何建立一个由多个分类模型组成的框架，而不是依赖于一个表现最佳的模型，以可靠地分类和识别 WDN 中的故障类型。
{"title":"Identifying failure types in cyber-physical water distribution networks using machine learning models","authors":"Utsav Parajuli, Sangmin Shin","doi":"10.2166/aqua.2024.264","DOIUrl":"https://doi.org/10.2166/aqua.2024.264","url":null,"abstract":"\u0000 \u0000 Water cyber-physical systems (CPSs) have experienced anomalies from cyber-physical attacks as well as conventional physical and operational failures (e.g., pipe leaks/bursts). In this regard, rapidly distinguishing and identifying a facing failure event from other possible failure events is necessary to take rapid emergency and recovery actions and, in turn, strengthen system's resilience. This paper investigated the performance of machine learning classification models – Support Vector Machine (SVM), Random Forest (RF), and artificial neural networks (ANNs) – to differentiate and identify failure events that can occur in a water distribution network (WDN). Datasets for model features related to tank water levels, nodal pressure, and water flow of pumps and valves were produced using hydraulic model simulation (WNTR and epanetCPA tools) for C-Town WDN under pipe leaks/bursts, cyber-attacks, and physical attacks. The evaluation of accuracy, precision, recall, and F1-score for the three models in failure type identification showed the variation of their performances depending on the specific failure types and data noise levels. Based on the findings, this study discussed insights into building a framework consisting of multiple classification models, rather than relying on a single best-performing model, for the reliable classification and identification of failure types in WDNs.","PeriodicalId":513288,"journal":{"name":"AQUA — Water Infrastructure, Ecosystems and Society","volume":"112 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140422253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shafqat Hussain Bhatti, Habib Ur Rehman, Muhammad Kaleem Sarwar, Muhammad Waqas Zaffar, Muhammad Awais Zafar, Muhammad Atiq Ur Rehman Tariq
Large orifices are constructed for dams to release water and sediments from reservoirs. Such structures are called submerged spillways. Numerous studies have investigated discharge coefficient, velocity coefficient, and head loss coefficient of large orifices; however, the literature lacks data on the upper and lower nappes of the jets from these orifices. In the present experimental study, the upper and lower nappes are investigated up to 80 m head at different gate openings. The observed minor deviation between the lower nappe profile and trajectory profile equation suggests sensitivity to different factors. The significant role of the coefficient of velocity, averaging at 0.926, highlights its impact on minor deviation. Subsequently, the impact of the solid bottom profile on the discharge coefficient and upper nappe profile are also examined. The results show improvement in discharge coefficient of a sharp-edged large orifice, which increased from 0.69 to 0.74. The results also indicate that the upper nappe profiles and United States Bureau of Reclamation (USBR) profiles are similar. The improvement in the upper nappe profile indicates the significant role of the solid bottom profile, which consequently has found to be helpful in defining the roof profile of an orifice spillway. .
{"title":"Analysis of upper and lower nappe profiles of large orifice for the design of bottom and roof profiles of high head orifice spillway","authors":"Shafqat Hussain Bhatti, Habib Ur Rehman, Muhammad Kaleem Sarwar, Muhammad Waqas Zaffar, Muhammad Awais Zafar, Muhammad Atiq Ur Rehman Tariq","doi":"10.2166/aqua.2024.034","DOIUrl":"https://doi.org/10.2166/aqua.2024.034","url":null,"abstract":"\u0000 \u0000 Large orifices are constructed for dams to release water and sediments from reservoirs. Such structures are called submerged spillways. Numerous studies have investigated discharge coefficient, velocity coefficient, and head loss coefficient of large orifices; however, the literature lacks data on the upper and lower nappes of the jets from these orifices. In the present experimental study, the upper and lower nappes are investigated up to 80 m head at different gate openings. The observed minor deviation between the lower nappe profile and trajectory profile equation suggests sensitivity to different factors. The significant role of the coefficient of velocity, averaging at 0.926, highlights its impact on minor deviation. Subsequently, the impact of the solid bottom profile on the discharge coefficient and upper nappe profile are also examined. The results show improvement in discharge coefficient of a sharp-edged large orifice, which increased from 0.69 to 0.74. The results also indicate that the upper nappe profiles and United States Bureau of Reclamation (USBR) profiles are similar. The improvement in the upper nappe profile indicates the significant role of the solid bottom profile, which consequently has found to be helpful in defining the roof profile of an orifice spillway. .","PeriodicalId":513288,"journal":{"name":"AQUA — Water Infrastructure, Ecosystems and Society","volume":"240 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140417752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Forecasting short-term water demands is one of the most critical needs of operating companies of urban water distribution networks. Water demands have a time series nature, and various factors affect their variations and patterns, which make it difficult to forecast. In this study, we first implemented a hybrid model of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to forecast urban water demand. These models include a combination of CNN with simple RNN (CNN-Simple RNN), CNN with the gate recurrent unit (CNN-GRU), and CNN with the long short-term memory. Then, we increased the number of CNN channels to achieve higher accuracy. The accuracy of the models increased with the number of CNN channels up to four. The evaluation metrics show that the CNN-GRU model is superior to other models. Ultimately, the four-channel CNN-GRU model demonstrated the highest accuracy, achieving a mean absolute percentage error (MAPE) of 1.65% for a 24-h forecasting horizon. The effects of the forecast horizon on the accuracy of the results were also investigated. The results show that the MAPE for a 1-h forecast horizon is 1.06% in four-channel CNN-GRU, and its value decreases with the amount of the forecast horizon.
{"title":"Deep learning–based short-term water demand forecasting in urban areas: a hybrid multichannel model","authors":"Hossein Namdari, S. M. Ashrafi, Ali Haghighi","doi":"10.2166/aqua.2024.200","DOIUrl":"https://doi.org/10.2166/aqua.2024.200","url":null,"abstract":"\u0000 \u0000 Forecasting short-term water demands is one of the most critical needs of operating companies of urban water distribution networks. Water demands have a time series nature, and various factors affect their variations and patterns, which make it difficult to forecast. In this study, we first implemented a hybrid model of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to forecast urban water demand. These models include a combination of CNN with simple RNN (CNN-Simple RNN), CNN with the gate recurrent unit (CNN-GRU), and CNN with the long short-term memory. Then, we increased the number of CNN channels to achieve higher accuracy. The accuracy of the models increased with the number of CNN channels up to four. The evaluation metrics show that the CNN-GRU model is superior to other models. Ultimately, the four-channel CNN-GRU model demonstrated the highest accuracy, achieving a mean absolute percentage error (MAPE) of 1.65% for a 24-h forecasting horizon. The effects of the forecast horizon on the accuracy of the results were also investigated. The results show that the MAPE for a 1-h forecast horizon is 1.06% in four-channel CNN-GRU, and its value decreases with the amount of the forecast horizon.","PeriodicalId":513288,"journal":{"name":"AQUA — Water Infrastructure, Ecosystems and Society","volume":"376 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140417471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The study demonstrates how to estimate evapotranspiration (ET) for the Western Rajasthan region of India utilizing remotely sensed images with the Surface Energy Balance Algorithm for Land (SEBAL). Landsat 8 and Moderate Resolution Imaging Spectroradiometer (MODIS) satellite inputs were used to compute seasonal and annual ET on the Google Earth Engine platform. The assessment utilizing the SEBAL algorithm, in combination with the Food and Agriculture Organization (FAO) Penman–Monteith (PM) and Hargreaves methods, demonstrates that SEBAL has adequate reliability for estimating ET for a spatially large extent in semi-arid regions when evaluated with the Hargreaves method. The values of R2, root-mean-square error (RMSE), and mean bias error (MBE) for FAO-PM were 0.63, 1.65 mm/day, and 1.28 mm/day, respectively. For the Hargreaves method, the values of R2, RMSE, and MBE were 0.96, 0.41 mm/day, and −0.31 mm/day, respectively. The study showed that the northern region witnessed the highest ET due to the availability of abundant surface water for irrigation. Overall, the results demonstrate the SEBAL model's effectiveness in estimating evapotranspiration. A downward trend in ET is observed in the region, mainly due to changing climatic conditions.
{"title":"Spatiotemporal trends and evapotranspiration estimation using an improvised SEBAL convergence method for the semi-arid region of Western Rajasthan, India","authors":"Dhruv Saxena, M. Choudhary, Gunwant Sharma","doi":"10.2166/aqua.2024.220","DOIUrl":"https://doi.org/10.2166/aqua.2024.220","url":null,"abstract":"\u0000 \u0000 The study demonstrates how to estimate evapotranspiration (ET) for the Western Rajasthan region of India utilizing remotely sensed images with the Surface Energy Balance Algorithm for Land (SEBAL). Landsat 8 and Moderate Resolution Imaging Spectroradiometer (MODIS) satellite inputs were used to compute seasonal and annual ET on the Google Earth Engine platform. The assessment utilizing the SEBAL algorithm, in combination with the Food and Agriculture Organization (FAO) Penman–Monteith (PM) and Hargreaves methods, demonstrates that SEBAL has adequate reliability for estimating ET for a spatially large extent in semi-arid regions when evaluated with the Hargreaves method. The values of R2, root-mean-square error (RMSE), and mean bias error (MBE) for FAO-PM were 0.63, 1.65 mm/day, and 1.28 mm/day, respectively. For the Hargreaves method, the values of R2, RMSE, and MBE were 0.96, 0.41 mm/day, and −0.31 mm/day, respectively. The study showed that the northern region witnessed the highest ET due to the availability of abundant surface water for irrigation. Overall, the results demonstrate the SEBAL model's effectiveness in estimating evapotranspiration. A downward trend in ET is observed in the region, mainly due to changing climatic conditions.","PeriodicalId":513288,"journal":{"name":"AQUA — Water Infrastructure, Ecosystems and Society","volume":"52 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140431576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The failure of bridges, attributed to bridge pier scouring, poses a significant challenge in ensuring safe and cost-effective design. Numerous laboratory and field experiments have been conducted to comprehend the mechanisms and predict the maximum equilibrium scour depth around bridge piers. Over the last eight decades, various empirical methods have been developed, with different authors incorporating diverse influencing parameters that significantly impact the estimation of equilibrium scour depth around bridge piers. This paper aims to consolidate (1) available experimental and field data sets on different types of bridge pier scouring, (2) the influence of flow and roughness parameters on both clear water scouring (CWS) and live bed scouring (LBS), and (3) existing empirical equations suitable for computing equilibrium scour depth around a bridge pier under CWS and LBS conditions. The presented research encompasses over 80 experimental/field data sets and more than 60 scour-predicting equations developed for CWS and LBS conditions in the past eight decades. For CWS, Neill (1964), CSU (1975), Yanmaz (1989), Ettema et al. (1998), and Pandey et al. (2018) are recommended.
{"title":"Scouring around bridge pier: a comprehensive analysis of scour depth predictive equations for clear-water and live-bed scouring conditions","authors":"Anubhav Baranwal, Bhabani Shankar Das","doi":"10.2166/aqua.2024.235","DOIUrl":"https://doi.org/10.2166/aqua.2024.235","url":null,"abstract":"\u0000 The failure of bridges, attributed to bridge pier scouring, poses a significant challenge in ensuring safe and cost-effective design. Numerous laboratory and field experiments have been conducted to comprehend the mechanisms and predict the maximum equilibrium scour depth around bridge piers. Over the last eight decades, various empirical methods have been developed, with different authors incorporating diverse influencing parameters that significantly impact the estimation of equilibrium scour depth around bridge piers. This paper aims to consolidate (1) available experimental and field data sets on different types of bridge pier scouring, (2) the influence of flow and roughness parameters on both clear water scouring (CWS) and live bed scouring (LBS), and (3) existing empirical equations suitable for computing equilibrium scour depth around a bridge pier under CWS and LBS conditions. The presented research encompasses over 80 experimental/field data sets and more than 60 scour-predicting equations developed for CWS and LBS conditions in the past eight decades. For CWS, Neill (1964), CSU (1975), Yanmaz (1989), Ettema et al. (1998), and Pandey et al. (2018) are recommended.","PeriodicalId":513288,"journal":{"name":"AQUA — Water Infrastructure, Ecosystems and Society","volume":"7 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140434938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. Abbaszadeh, R. Daneshfaraz, Veli Sume, John Abraham
This investigation focuses on flow energy, a crucial parameter in the design of water structures such as channels. The research endeavors to explore the relative energy loss (ΔEAB/EA) in a constricted flow path of varying widths, employing Support Vector Machine (SVM), Artificial Neural Network (ANN), Gene Expression Programming (GEP), Multiple Adaptive Regression Splines (MARS), M5 and Random Forest (RF) models. Experiments span a Froude number range from 2.85 to 8.85. The experimental findings indicate that the ΔEAB/EA exceeds that observed in a classical hydraulic jump with constriction section. Within the SVM model, the linear kernel emerges as the best predictor of ΔEAB/EA, outperforming polynomial, radial basis function (RBF), and sigmoid kernels. In addition, in the ANN model, the MLP network was more accurate compared to the RBF network. The results indicate that the relationship proposed by the MARS model can play a significant role resulting in high accuracy compared to the non-linear regression relationship in predicting the target parameter. Upon comprehensive evaluation, the ANN method emerges as the most promising among the candidates, yielding superior performance compared to the other models. The testing phase results for the ANN-MLP are noteworthy, with R = 0.997, average RE% = 0.63%, RMSE = 0.0069, BIAS = −0.0004, DR = 0.999, SI = 0.0098 and KGE = 0.995.
{"title":"Experimental investigation and application of soft computing models for predicting flow energy loss in arc-shaped constrictions","authors":"H. Abbaszadeh, R. Daneshfaraz, Veli Sume, John Abraham","doi":"10.2166/aqua.2024.010","DOIUrl":"https://doi.org/10.2166/aqua.2024.010","url":null,"abstract":"\u0000 \u0000 This investigation focuses on flow energy, a crucial parameter in the design of water structures such as channels. The research endeavors to explore the relative energy loss (ΔEAB/EA) in a constricted flow path of varying widths, employing Support Vector Machine (SVM), Artificial Neural Network (ANN), Gene Expression Programming (GEP), Multiple Adaptive Regression Splines (MARS), M5 and Random Forest (RF) models. Experiments span a Froude number range from 2.85 to 8.85. The experimental findings indicate that the ΔEAB/EA exceeds that observed in a classical hydraulic jump with constriction section. Within the SVM model, the linear kernel emerges as the best predictor of ΔEAB/EA, outperforming polynomial, radial basis function (RBF), and sigmoid kernels. In addition, in the ANN model, the MLP network was more accurate compared to the RBF network. The results indicate that the relationship proposed by the MARS model can play a significant role resulting in high accuracy compared to the non-linear regression relationship in predicting the target parameter. Upon comprehensive evaluation, the ANN method emerges as the most promising among the candidates, yielding superior performance compared to the other models. The testing phase results for the ANN-MLP are noteworthy, with R = 0.997, average RE% = 0.63%, RMSE = 0.0069, BIAS = −0.0004, DR = 0.999, SI = 0.0098 and KGE = 0.995.","PeriodicalId":513288,"journal":{"name":"AQUA — Water Infrastructure, Ecosystems and Society","volume":"13 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140436377","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Non-revenue water (NRW) in Luangprabang City, Laos, has been high and fluctuating. Therefore, we aimed to analyze the factors influencing the fluctuation of NRW in two district-metered areas (DMAs). The average NRWs for 16–17 months in DMA-1 and DMA-2 were 28.92 and 43.92%, respectively, whereas the coefficients of variations of the monthly NRWs were high at 49.7 and 11.7%, respectively. Among the factors causing the fluctuation of NRW, meter inaccuracies were less than 2%, although inaccessibility to customer meters was high at 46.4 and 38.7% in DMA-1 and DMA-2, respectively. However, the meter reading intervals had little influence on billed water consumption. Using the IWA Water Balance table, the apparent loss was estimated as 2.6%, whereas the real loss (24.9%) was the main component of NRW (27.5%) in DMA-2. The monthly and 3–7-month moving averages of NRW were inversely correlated with billed water consumption, indicating that both volumetric and percentage NRWs were strongly influenced by fluctuations in billed water consumption. Network simulation verified that high inaccessibility to customer meters, particularly during the COVID-19 lockdown, caused large fluctuations in billed water consumption and NRWs. Therefore, access to customer water meters should be improved to alleviate the fluctuation of NRW.
{"title":"Analysis of the factors influencing the fluctuation of non-revenue water in Luangprabang City, Laos","authors":"Sunti Chandaeng, Benyapa Sawangjang, Shinobu Kazama, Satoshi Takizawa","doi":"10.2166/aqua.2024.246","DOIUrl":"https://doi.org/10.2166/aqua.2024.246","url":null,"abstract":"\u0000 \u0000 Non-revenue water (NRW) in Luangprabang City, Laos, has been high and fluctuating. Therefore, we aimed to analyze the factors influencing the fluctuation of NRW in two district-metered areas (DMAs). The average NRWs for 16–17 months in DMA-1 and DMA-2 were 28.92 and 43.92%, respectively, whereas the coefficients of variations of the monthly NRWs were high at 49.7 and 11.7%, respectively. Among the factors causing the fluctuation of NRW, meter inaccuracies were less than 2%, although inaccessibility to customer meters was high at 46.4 and 38.7% in DMA-1 and DMA-2, respectively. However, the meter reading intervals had little influence on billed water consumption. Using the IWA Water Balance table, the apparent loss was estimated as 2.6%, whereas the real loss (24.9%) was the main component of NRW (27.5%) in DMA-2. The monthly and 3–7-month moving averages of NRW were inversely correlated with billed water consumption, indicating that both volumetric and percentage NRWs were strongly influenced by fluctuations in billed water consumption. Network simulation verified that high inaccessibility to customer meters, particularly during the COVID-19 lockdown, caused large fluctuations in billed water consumption and NRWs. Therefore, access to customer water meters should be improved to alleviate the fluctuation of NRW.","PeriodicalId":513288,"journal":{"name":"AQUA — Water Infrastructure, Ecosystems and Society","volume":"39 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140435866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：