Pub Date : 2023-09-07DOI: 10.1080/1573062x.2023.2254745
Roman Cieśliński, Michał Szydłowski, I. Chlost, Patrycja Mikos-Studnicka
{"title":"Hazards of a flooding event in the city of Gdansk and possible forms of preventing the phenomenon – case study","authors":"Roman Cieśliński, Michał Szydłowski, I. Chlost, Patrycja Mikos-Studnicka","doi":"10.1080/1573062x.2023.2254745","DOIUrl":"https://doi.org/10.1080/1573062x.2023.2254745","url":null,"abstract":"","PeriodicalId":49392,"journal":{"name":"Urban Water Journal","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48150442","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-06DOI: 10.1080/1573062X.2023.2254739
Wenhao Wang, Xinxin Xu, Jingguo Cao, Ming Zeng, Wu Zhang
ABSTRACT This study investigated the effect of environmental parameters on microbial-induced concrete corrosion during three corrosion stages. The corrosion effects and influencing factors in three corrosion stages were deeply analyzed and predicted, and the mechanism of microbial corrosion was summarized. When the H2S concentration was lower than about 15.0 mg/m3, the corrosion was maintained in stage II, which greatly delays the intensification of corrosion. In stage III, the H2S concentration has the significantly accelerate the corrosion rate. Additionally, incorporating min, max and mean values of input parameters greatly improved the accuracy of machine learning predictions of corrosion rates (R2 >0.99). Acidithiobacillus was found to be dominant in the microbial community at H2S concentrations of 12.0–37.5 mg/m3, and increased temperature promoted the reproduction of Acidithiobacillus.
{"title":"Deciphering and predict corrosion effect, influencing factors and microbial mechanism of sewer concrete corrosion based on extensive data analysis and machine learning","authors":"Wenhao Wang, Xinxin Xu, Jingguo Cao, Ming Zeng, Wu Zhang","doi":"10.1080/1573062X.2023.2254739","DOIUrl":"https://doi.org/10.1080/1573062X.2023.2254739","url":null,"abstract":"ABSTRACT This study investigated the effect of environmental parameters on microbial-induced concrete corrosion during three corrosion stages. The corrosion effects and influencing factors in three corrosion stages were deeply analyzed and predicted, and the mechanism of microbial corrosion was summarized. When the H2S concentration was lower than about 15.0 mg/m3, the corrosion was maintained in stage II, which greatly delays the intensification of corrosion. In stage III, the H2S concentration has the significantly accelerate the corrosion rate. Additionally, incorporating min, max and mean values of input parameters greatly improved the accuracy of machine learning predictions of corrosion rates (R2 >0.99). Acidithiobacillus was found to be dominant in the microbial community at H2S concentrations of 12.0–37.5 mg/m3, and increased temperature promoted the reproduction of Acidithiobacillus.","PeriodicalId":49392,"journal":{"name":"Urban Water Journal","volume":"20 1","pages":"1219 - 1230"},"PeriodicalIF":2.7,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44586901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-06DOI: 10.1080/1573062X.2023.2251973
E. Nieuwenhuis, Hans de Bruijn, E. Cuppen, J. Langeveld
ABSTRACT Urban water systems worldwide need integrated, cross-sectoral innovations to anticipate developments like climate change and population growth. Development and implementation of such innovations is challenging due to the operational and sectoral mindset of organizations in which these innovations take place. This study uses the concept of ambidexterity to get a better understanding of how organizations responsible for urban water management deal with the tension between operation and the need for innovation. We focused on Amsterdam and Rotterdam, two Dutch cities that are global frontrunners in urban water management. Combining a desk study with 25 semi-structured interviews, we found four mechanisms to manage innovation and operation tensions: network, hierarchical, process and human-resource mechnanisms. Different from the literature on ambidexterity, our empirical findings show that the connection between operation and innovation is dominated by networks rather than by executives. Hierarchical mechanisms could be used to complement this, catalyzing innovation or formalizing it.
{"title":"Understanding cross-sectoral innovations for urban water management through the lens of organizational ambidexterity","authors":"E. Nieuwenhuis, Hans de Bruijn, E. Cuppen, J. Langeveld","doi":"10.1080/1573062X.2023.2251973","DOIUrl":"https://doi.org/10.1080/1573062X.2023.2251973","url":null,"abstract":"ABSTRACT Urban water systems worldwide need integrated, cross-sectoral innovations to anticipate developments like climate change and population growth. Development and implementation of such innovations is challenging due to the operational and sectoral mindset of organizations in which these innovations take place. This study uses the concept of ambidexterity to get a better understanding of how organizations responsible for urban water management deal with the tension between operation and the need for innovation. We focused on Amsterdam and Rotterdam, two Dutch cities that are global frontrunners in urban water management. Combining a desk study with 25 semi-structured interviews, we found four mechanisms to manage innovation and operation tensions: network, hierarchical, process and human-resource mechnanisms. Different from the literature on ambidexterity, our empirical findings show that the connection between operation and innovation is dominated by networks rather than by executives. Hierarchical mechanisms could be used to complement this, catalyzing innovation or formalizing it.","PeriodicalId":49392,"journal":{"name":"Urban Water Journal","volume":"20 1","pages":"1183 - 1195"},"PeriodicalIF":2.7,"publicationDate":"2023-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48031450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-05DOI: 10.1080/1573062X.2023.2251952
Si-Liang Zhao, Shaogang Liu, Bo Qiu, Zhou Hong, Dan Zhao, Liqiang Dong
ABSTRACT In order to solve the problem of inconspicuous leakage signal characteristics under external noise interference, a leakage detection method based on the combination of variational modal decomposition (VMD) and support vector machine (SVM) is proposed. The method first calculates the spearman correlation coefficients (SCC) of multiple intrinsic modal components (IMFs) obtained by VMD with the source signal, then extracts the energy and central frequency features of IMFs with larger SCC, and finally performs leak detection using the SVM classifier. The experimental results show that the VMD-SVM method can effectively perform leak detection with an accuracy of 98.27%. The accuracy of the VMD-SVM method proposed in this paper is improved by 6.5%, 5.63% and 10.39% compared to the time-frequency (TF) feature SVM, empirical modal decomposition (EMD) feature SVM and wavelet (DWT) feature SVM, methods, respectively. In addition, feature sensitivities are analyzed to reduce model complexity while ensuring accuracy.
{"title":"Leak detection method of liquid-filled pipeline based on VMD and SVM","authors":"Si-Liang Zhao, Shaogang Liu, Bo Qiu, Zhou Hong, Dan Zhao, Liqiang Dong","doi":"10.1080/1573062X.2023.2251952","DOIUrl":"https://doi.org/10.1080/1573062X.2023.2251952","url":null,"abstract":"ABSTRACT In order to solve the problem of inconspicuous leakage signal characteristics under external noise interference, a leakage detection method based on the combination of variational modal decomposition (VMD) and support vector machine (SVM) is proposed. The method first calculates the spearman correlation coefficients (SCC) of multiple intrinsic modal components (IMFs) obtained by VMD with the source signal, then extracts the energy and central frequency features of IMFs with larger SCC, and finally performs leak detection using the SVM classifier. The experimental results show that the VMD-SVM method can effectively perform leak detection with an accuracy of 98.27%. The accuracy of the VMD-SVM method proposed in this paper is improved by 6.5%, 5.63% and 10.39% compared to the time-frequency (TF) feature SVM, empirical modal decomposition (EMD) feature SVM and wavelet (DWT) feature SVM, methods, respectively. In addition, feature sensitivities are analyzed to reduce model complexity while ensuring accuracy.","PeriodicalId":49392,"journal":{"name":"Urban Water Journal","volume":"20 1","pages":"1169 - 1182"},"PeriodicalIF":2.7,"publicationDate":"2023-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45960133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-01DOI: 10.1080/1573062X.2023.2253215
Adane Sirage Ali, Sirak Robele Gari, Michaela L Goodson, Claire L. Walsh, B. K. Dessie, A. Ambelu
ABSTRACT Wastewater irrigation may reintroduce fecal pathogens to households and cause drinking water contamination. The aim of this study was to assess the effect of wastewater irrigation on the quality of drinking water among wastewater-irrigating urban farming households. Drinking water samples from 52 households of farming communities in 19 sampling sites were collected twice at PoS and PoC. The microbial quality of the water was assessed using E. coli counted by membrane filtration. Samples collected from exposed households at PoC were 100% positive for E. coli with mean E. coli at PoC increased 10× from the PoS and 3× higher compared to PoC in the unexposed households. The absence of hand washing water (ATE = 8.14), water storing (ATE = 7.75) and intermittent water supply (ATE = 6.25) were significant factors for the increased E. coli at PoC. Breaking the path of the pathogens from the farm to the house and from PoS to PoC needsintervention.
{"title":"The impact of wastewater-irrigated urban agriculture on microbial quality of drinking water at household level in Addis Ababa, Ethiopia","authors":"Adane Sirage Ali, Sirak Robele Gari, Michaela L Goodson, Claire L. Walsh, B. K. Dessie, A. Ambelu","doi":"10.1080/1573062X.2023.2253215","DOIUrl":"https://doi.org/10.1080/1573062X.2023.2253215","url":null,"abstract":"ABSTRACT Wastewater irrigation may reintroduce fecal pathogens to households and cause drinking water contamination. The aim of this study was to assess the effect of wastewater irrigation on the quality of drinking water among wastewater-irrigating urban farming households. Drinking water samples from 52 households of farming communities in 19 sampling sites were collected twice at PoS and PoC. The microbial quality of the water was assessed using E. coli counted by membrane filtration. Samples collected from exposed households at PoC were 100% positive for E. coli with mean E. coli at PoC increased 10× from the PoS and 3× higher compared to PoC in the unexposed households. The absence of hand washing water (ATE = 8.14), water storing (ATE = 7.75) and intermittent water supply (ATE = 6.25) were significant factors for the increased E. coli at PoC. Breaking the path of the pathogens from the farm to the house and from PoS to PoC needsintervention.","PeriodicalId":49392,"journal":{"name":"Urban Water Journal","volume":"20 1","pages":"1207 - 1218"},"PeriodicalIF":2.7,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44534449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-09-01DOI: 10.1080/1573062X.2023.2252807
Xiaoyu Shi, Zijing Liu, Carlos Velazquez, Haifeng Jia
ABSTRACT To mitigate urban drainage network pressures and seek sustainable solutions, novel tools like graph theory are presently being studied. This paper presents a systematic literature review of graph-based approaches through an intensive content analysis based on 144 published papers. Comparisons are drawn between water distribution networks and urban drainage networks in terms of convergence and divergence, revealing more divergence in network topological characteristics but more convergence in functional features. The findings provide convincing evidence for applications in UDNs, despite limited numbers and depth. Subsequently, a comparison between graph-based and hydraulic-based approaches is shown, demonstrating distinct advantages of graph-based methods in cases with limited data and time constraints. Based on these findings, the paper suggests several potential directions, including the improvement of parameter calculation formulas, the definition of parameter mathematical ranges and the popularization of recommended values. Finally, the paper examines its own shortcomings.
{"title":"The role of graph-based methods in urban drainage networks (UDNs): review and directions for future","authors":"Xiaoyu Shi, Zijing Liu, Carlos Velazquez, Haifeng Jia","doi":"10.1080/1573062X.2023.2252807","DOIUrl":"https://doi.org/10.1080/1573062X.2023.2252807","url":null,"abstract":"ABSTRACT To mitigate urban drainage network pressures and seek sustainable solutions, novel tools like graph theory are presently being studied. This paper presents a systematic literature review of graph-based approaches through an intensive content analysis based on 144 published papers. Comparisons are drawn between water distribution networks and urban drainage networks in terms of convergence and divergence, revealing more divergence in network topological characteristics but more convergence in functional features. The findings provide convincing evidence for applications in UDNs, despite limited numbers and depth. Subsequently, a comparison between graph-based and hydraulic-based approaches is shown, demonstrating distinct advantages of graph-based methods in cases with limited data and time constraints. Based on these findings, the paper suggests several potential directions, including the improvement of parameter calculation formulas, the definition of parameter mathematical ranges and the popularization of recommended values. Finally, the paper examines its own shortcomings.","PeriodicalId":49392,"journal":{"name":"Urban Water Journal","volume":"20 1","pages":"1095 - 1109"},"PeriodicalIF":2.7,"publicationDate":"2023-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48546634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-31DOI: 10.1080/1573062X.2023.2241437
I. Fisher, G. Kastl, A. Sathasivan
ABSTRACT Chlorine concentrations in water distribution systems are generally predicted by combined models of reactions in bulk water and at pipe walls. The structure of the widely used EPANET wall-reaction models is questioned, as they do not reproduce the variation in wall-reaction rate with decreasing chlorine observed in real pipelines. The microbially mediated wall-reaction model (EXPBIO) is structurally valid. EXPBIO was extended to calculate the mass-transfer coefficient in individual pipes, rather than using a single fitted value. Smooth- and rough-pipe versions were formally validated against observed chlorine data from the Mirrabooka pipeline, where rough-pipe predictions better matched lower observed chlorine concentrations. In a medium-sized rough pipe, the mass-transfer coefficient doubled between 10 and 30°C. In the real pipeline, chlorine concentration decreased much faster with distance downstream at higher temperature, due to increasing microbial activity and mass-transfer of chlorine. System simulations to search for improved seasonal chlorine dosing strategies need to include these effects.
{"title":"Validity of chlorine-wall reaction models for drinking water distribution systems","authors":"I. Fisher, G. Kastl, A. Sathasivan","doi":"10.1080/1573062X.2023.2241437","DOIUrl":"https://doi.org/10.1080/1573062X.2023.2241437","url":null,"abstract":"ABSTRACT Chlorine concentrations in water distribution systems are generally predicted by combined models of reactions in bulk water and at pipe walls. The structure of the widely used EPANET wall-reaction models is questioned, as they do not reproduce the variation in wall-reaction rate with decreasing chlorine observed in real pipelines. The microbially mediated wall-reaction model (EXPBIO) is structurally valid. EXPBIO was extended to calculate the mass-transfer coefficient in individual pipes, rather than using a single fitted value. Smooth- and rough-pipe versions were formally validated against observed chlorine data from the Mirrabooka pipeline, where rough-pipe predictions better matched lower observed chlorine concentrations. In a medium-sized rough pipe, the mass-transfer coefficient doubled between 10 and 30°C. In the real pipeline, chlorine concentration decreased much faster with distance downstream at higher temperature, due to increasing microbial activity and mass-transfer of chlorine. System simulations to search for improved seasonal chlorine dosing strategies need to include these effects.","PeriodicalId":49392,"journal":{"name":"Urban Water Journal","volume":"20 1","pages":"1157 - 1168"},"PeriodicalIF":2.7,"publicationDate":"2023-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47575963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-28DOI: 10.1080/1573062X.2023.2253213
D. Owusu-Manu, S. Seidu, R. O. Asiedu, J. Buertey, A. K. Danso, D. J. Edwards, K. Nkrumah
ABSTRACT Assessments of urban green drainage infrastructure (UGDI) have always been a headache in contemporary times which is a roadblock to enticing investors. This study prioritized the underlying sustainability indicators of UGDI systems in Ghana. After an exhaustive literature review, some identified sustainability indicators were compounded into semi-structured questionnaires. Sixty-two built environment professionals were asked to rate the significance of each indicator. A parametric test was used to prioritize the indicators. The results indicated that the most significant underlying sustainability indicators were; ‘Flood control’, ‘Compliance with sustainable development goals’, ‘multi-functionality’, ‘energy efficiency and GHG emissions’ and ‘Initial Construction Cost’. To understand how UGDI performs with regards to flood and pollution mitigation, specific geographical performance indicators are required. This is an under-explored area in the Ghanaian context. Hence, the indicators espoused in this study serve as a starting point for the development of appropriate frameworks to aid the implementation of UGDI.
{"title":"Prioritization of the key underlying sustainability indicators of urban green drainage infrastructure systems","authors":"D. Owusu-Manu, S. Seidu, R. O. Asiedu, J. Buertey, A. K. Danso, D. J. Edwards, K. Nkrumah","doi":"10.1080/1573062X.2023.2253213","DOIUrl":"https://doi.org/10.1080/1573062X.2023.2253213","url":null,"abstract":"ABSTRACT Assessments of urban green drainage infrastructure (UGDI) have always been a headache in contemporary times which is a roadblock to enticing investors. This study prioritized the underlying sustainability indicators of UGDI systems in Ghana. After an exhaustive literature review, some identified sustainability indicators were compounded into semi-structured questionnaires. Sixty-two built environment professionals were asked to rate the significance of each indicator. A parametric test was used to prioritize the indicators. The results indicated that the most significant underlying sustainability indicators were; ‘Flood control’, ‘Compliance with sustainable development goals’, ‘multi-functionality’, ‘energy efficiency and GHG emissions’ and ‘Initial Construction Cost’. To understand how UGDI performs with regards to flood and pollution mitigation, specific geographical performance indicators are required. This is an under-explored area in the Ghanaian context. Hence, the indicators espoused in this study serve as a starting point for the development of appropriate frameworks to aid the implementation of UGDI.","PeriodicalId":49392,"journal":{"name":"Urban Water Journal","volume":"20 1","pages":"1196 - 1206"},"PeriodicalIF":2.7,"publicationDate":"2023-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48680470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-09DOI: 10.1080/1573062X.2023.2217433
A. Pinheiro, S. Vaz, L. Monteiro, M. Almeida, D. Covas
ABSTRACT This paper investigates the effect of different types of structural and operational measures on water mixing and renewal time in circular and rectangular cross-section water storage tanks, aiming at a better understanding of the flow dynamics to find practicable solutions to improve their design, rehabilitation and operation. An experimental programme, including traditional tracer and dye tracer tests, was carried out in small-scale tanks for different configurations and operating conditions. Two tanks were tested with and without interior structures, with the inlet/outlet pipes at different locations and for constant and variable water level. The main findings are that: i) the most effective measure is operating with fill-and-draw cycles, however, for tanks operated nearly full structural measures are recommendable; ii) reducing the inlet pipe diameter and installing nozzles near the tank bottom improve the mixing conditions; iii) the use of baffles is recommendable when the inlet and outlet pipes are very close.
{"title":"Improving mixing and renewal in drinking water storage tanks: lessons learnt and practical measures","authors":"A. Pinheiro, S. Vaz, L. Monteiro, M. Almeida, D. Covas","doi":"10.1080/1573062X.2023.2217433","DOIUrl":"https://doi.org/10.1080/1573062X.2023.2217433","url":null,"abstract":"ABSTRACT This paper investigates the effect of different types of structural and operational measures on water mixing and renewal time in circular and rectangular cross-section water storage tanks, aiming at a better understanding of the flow dynamics to find practicable solutions to improve their design, rehabilitation and operation. An experimental programme, including traditional tracer and dye tracer tests, was carried out in small-scale tanks for different configurations and operating conditions. Two tanks were tested with and without interior structures, with the inlet/outlet pipes at different locations and for constant and variable water level. The main findings are that: i) the most effective measure is operating with fill-and-draw cycles, however, for tanks operated nearly full structural measures are recommendable; ii) reducing the inlet pipe diameter and installing nozzles near the tank bottom improve the mixing conditions; iii) the use of baffles is recommendable when the inlet and outlet pipes are very close.","PeriodicalId":49392,"journal":{"name":"Urban Water Journal","volume":"20 1","pages":"897 - 909"},"PeriodicalIF":2.7,"publicationDate":"2023-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45453925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-09DOI: 10.1080/1573062X.2023.2217430
L. V. Nguyen, S. Razak
ABSTRACT Predicting the structural condition of sewer pipes plays a vital role in the predictive maintenance of sewer pipes and renewal plans of many water utilities. This study explores the simultaneous utilization of physical and environmental features of sewer pipes in sewer structural condition prediction. Three (3) hybrid machine learning models which are the combination of Bagging (BG), Dagging (DG), and Rotation Forest (RotF) ensembles with a J48 Decision Tree (J48DT) based classifier were used to predict sewer pipe conditions in Ålesund city, Norway. The classification performance of the machine learning models was evaluated using the area under the receiver operating characteristic (AUC-ROC) and the area under the precision-recall (AUC-PRC) curves. The RotF-J48DT model had the highest (AUC-ROC = 0.857, AUC-PRC = 0.918) values, followed by the BG-J48DT, and the base classifier J48DT. The RotF-J48DT hybrid model should be considered when predicting the condition of sewer pipes in the study area.
{"title":"Predicting sewer structural condition using hybrid machine learning algorithms","authors":"L. V. Nguyen, S. Razak","doi":"10.1080/1573062X.2023.2217430","DOIUrl":"https://doi.org/10.1080/1573062X.2023.2217430","url":null,"abstract":"ABSTRACT Predicting the structural condition of sewer pipes plays a vital role in the predictive maintenance of sewer pipes and renewal plans of many water utilities. This study explores the simultaneous utilization of physical and environmental features of sewer pipes in sewer structural condition prediction. Three (3) hybrid machine learning models which are the combination of Bagging (BG), Dagging (DG), and Rotation Forest (RotF) ensembles with a J48 Decision Tree (J48DT) based classifier were used to predict sewer pipe conditions in Ålesund city, Norway. The classification performance of the machine learning models was evaluated using the area under the receiver operating characteristic (AUC-ROC) and the area under the precision-recall (AUC-PRC) curves. The RotF-J48DT model had the highest (AUC-ROC = 0.857, AUC-PRC = 0.918) values, followed by the BG-J48DT, and the base classifier J48DT. The RotF-J48DT hybrid model should be considered when predicting the condition of sewer pipes in the study area.","PeriodicalId":49392,"journal":{"name":"Urban Water Journal","volume":"20 1","pages":"882 - 896"},"PeriodicalIF":2.7,"publicationDate":"2023-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41872589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}