Christian Ortiz-Lopez, Andres Torres, Christian Bouchard, Manuel Rodriguez
Abstract Rainfall and increased river flow can deteriorate raw water (RW) quality parameters such as turbidity and UV absorbance at 254 nm. This study aims to develop a methodology for integrating both time-lagged watershed rainfall and river flow data into machine learning models of the quality of RW supplying a drinking water treatment plant (DWTP). Spearman's rank non-parametric cross-correlation analyses were performed using both river flow and rain in the watershed and RW data from the water intake. Then, RW turbidity and RW UV254 were modelled, using a support vector regression (SVR) and an artificial neural network (ANN) under several prediction scenarios with time-lagged variables. River flow presented a very strong correlation with RW quality, whereas rainfall showed a moderate correlation. Time lags with maximum correlations between flow data and turbidity were a few hours, while for UV254, they were between 2 and 4 days, demonstrating varied time lags and a complex behaviour. The best performing scenario was the one that used time-lagged watershed rainfall and river flow as input data. ANN performed better for both turbidity and UV254 than SVR. Results from this study suggest the possibility for new modelling strategies and more accurate chemical dosing for the removal of key contaminants.
{"title":"A methodology for integrating time-lagged rainfall and river flow data into machine learning models to improve prediction of quality parameters of raw water supplying a treatment plant","authors":"Christian Ortiz-Lopez, Andres Torres, Christian Bouchard, Manuel Rodriguez","doi":"10.2166/hydro.2023.122","DOIUrl":"https://doi.org/10.2166/hydro.2023.122","url":null,"abstract":"Abstract Rainfall and increased river flow can deteriorate raw water (RW) quality parameters such as turbidity and UV absorbance at 254 nm. This study aims to develop a methodology for integrating both time-lagged watershed rainfall and river flow data into machine learning models of the quality of RW supplying a drinking water treatment plant (DWTP). Spearman's rank non-parametric cross-correlation analyses were performed using both river flow and rain in the watershed and RW data from the water intake. Then, RW turbidity and RW UV254 were modelled, using a support vector regression (SVR) and an artificial neural network (ANN) under several prediction scenarios with time-lagged variables. River flow presented a very strong correlation with RW quality, whereas rainfall showed a moderate correlation. Time lags with maximum correlations between flow data and turbidity were a few hours, while for UV254, they were between 2 and 4 days, demonstrating varied time lags and a complex behaviour. The best performing scenario was the one that used time-lagged watershed rainfall and river flow as input data. ANN performed better for both turbidity and UV254 than SVR. Results from this study suggest the possibility for new modelling strategies and more accurate chemical dosing for the removal of key contaminants.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135325965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Salinity is of paramount importance in shaping water quality, ecosystem health, and the capacity to sustain diverse human and environmental demands in estuarine environments. Electrical conductivity (EC) is commonly utilized as an indirect measure of salinity, serving as a proxy for estimating other ion constituents within the Delta. This study investigates and contrasts four machine learning (ML) models for approximating ion constituent concentrations based on EC measurements, emphasizing the enhancement of conversion for constituents exhibiting pronounced non-linear relationships with EC. Among the four models, the artificial neural network (ANN) model outshines the others in predicting ion constituents from EC, especially for those displaying strong non-linear relationships with EC. All four ML models surpass traditional parametric regression equations in terms of accuracy in estimating ion concentrations. The K-fold cross-validation method is utilized to evaluate the reliability of the ANN model, ensuring a comprehensive appraisal of its performance. Furthermore, an interactive web-browser-based dashboard is developed, catering to users with or without programming expertise, enabling ion level simulation within the Delta. By furnishing more precise ion constituent estimations, this research enriches the understanding of salinity's effects on water quality in the Delta and fosters well-informed water management decisions.
{"title":"Modeling ion constituents in the Sacramento-San Joaquin Delta using multiple machine learning approaches","authors":"Peyman Namadi, Minxue He, Prabhjot Sandhu","doi":"10.2166/hydro.2023.158","DOIUrl":"https://doi.org/10.2166/hydro.2023.158","url":null,"abstract":"Abstract Salinity is of paramount importance in shaping water quality, ecosystem health, and the capacity to sustain diverse human and environmental demands in estuarine environments. Electrical conductivity (EC) is commonly utilized as an indirect measure of salinity, serving as a proxy for estimating other ion constituents within the Delta. This study investigates and contrasts four machine learning (ML) models for approximating ion constituent concentrations based on EC measurements, emphasizing the enhancement of conversion for constituents exhibiting pronounced non-linear relationships with EC. Among the four models, the artificial neural network (ANN) model outshines the others in predicting ion constituents from EC, especially for those displaying strong non-linear relationships with EC. All four ML models surpass traditional parametric regression equations in terms of accuracy in estimating ion concentrations. The K-fold cross-validation method is utilized to evaluate the reliability of the ANN model, ensuring a comprehensive appraisal of its performance. Furthermore, an interactive web-browser-based dashboard is developed, catering to users with or without programming expertise, enabling ion level simulation within the Delta. By furnishing more precise ion constituent estimations, this research enriches the understanding of salinity's effects on water quality in the Delta and fosters well-informed water management decisions.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":"434 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135869990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract This article proposes a multi-head attention flood forecasting model (MHAFFM) that combines a multi-head attention mechanism with multiple linear regression for flood forecasting. Compared to LSTM-based models, MHAFFM enables precise and stable multi-hour flood forecasting while maintaining an interpretable forecasting process. First, the model utilizes characteristics of full-batch stable input data in multiple linear regression to solve the problem of oscillation in the prediction results of existing models. Second, full-batch information is connected to the multi-head attention architecture to improve the model's ability to process and interpret high-dimensional information. Finally, the model accurately and stably predicts future flood processes through linear layers. The model is applied to Dawen River Basin in Shandong, China, and experimental results show that the MHAFFM model, compared to three benchmarking models, namely, LSTM, BOA-LSTM, and MHAM-LSTM, significantly improves the prediction performance under different lead time scenarios while maintaining good stability and interpretability. Taking Nash–Sutcliffe efficiency index as an example, under a lead time of 3 h, the MHAFFM model exhibits improvements of 8.85, 3.71, and 10.29% compared to the three benchmarking models, respectively. In conclusion, this research enhances the credibility of deep learning in the field of hydrology and provides a new approach for its application.
{"title":"A new stable and interpretable flood forecasting model combining multi-head attention mechanism and multiple linear regression","authors":"Yi-yang Wang, Wenchuan Wang, Kwok-wing Chau, Dong-mei Xu, Hong-fei Zang, Chang-jun Liu, Qiang Ma","doi":"10.2166/hydro.2023.160","DOIUrl":"https://doi.org/10.2166/hydro.2023.160","url":null,"abstract":"Abstract This article proposes a multi-head attention flood forecasting model (MHAFFM) that combines a multi-head attention mechanism with multiple linear regression for flood forecasting. Compared to LSTM-based models, MHAFFM enables precise and stable multi-hour flood forecasting while maintaining an interpretable forecasting process. First, the model utilizes characteristics of full-batch stable input data in multiple linear regression to solve the problem of oscillation in the prediction results of existing models. Second, full-batch information is connected to the multi-head attention architecture to improve the model's ability to process and interpret high-dimensional information. Finally, the model accurately and stably predicts future flood processes through linear layers. The model is applied to Dawen River Basin in Shandong, China, and experimental results show that the MHAFFM model, compared to three benchmarking models, namely, LSTM, BOA-LSTM, and MHAM-LSTM, significantly improves the prediction performance under different lead time scenarios while maintaining good stability and interpretability. Taking Nash–Sutcliffe efficiency index as an example, under a lead time of 3 h, the MHAFFM model exhibits improvements of 8.85, 3.71, and 10.29% compared to the three benchmarking models, respectively. In conclusion, this research enhances the credibility of deep learning in the field of hydrology and provides a new approach for its application.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136106000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Sediment concentration (SC) monitoring has always been a pressing issue in water resource management, as many existing instruments still face challenges in accurately measuring due to environmental factors and instrument limitations. A robust technology is worth presenting to apply in the field site. This study firstly uses mean-absolute-error (MAE), root-mean-square error (RMSE), correlation coefficient (CC), and Nash–Sutcliffe efficiency coefficient (NSE) to describe the performance of the proposed convolutional neural network (CNN). Moreover, adapting the ensemble learning concept to compare the multiple machine learning (ML) approaches, the CNN presents the highest predicted accuracy, 91%, better than SVM (79%), VGG19 (63%) and ResNet50 (35%). As a result, the proposed CNN framework can appropriately apply the monitoring needs. The primary purpose is to develop a simple, accurate, and stable SC monitoring technology. Instead of some complex architectures, a simple and small neural network is adopted to implement real-time application (RTA). Via our design, such a traditional but critical issue can be improved to a new state. For example, by incorporating the concept of the Internet of Things (IoT) with our design, the distributed computing system for large-scale environmental monitoring can be realized quickly and easily.
{"title":"Development of a lightweight convolutional neural network-based visual model for sediment concentration prediction by incorporating the IoT concept","authors":"ChengChia Huang, Che-Cheng Chang, Chiao-Ming Chang, Ming-Han Tsai","doi":"10.2166/hydro.2023.215","DOIUrl":"https://doi.org/10.2166/hydro.2023.215","url":null,"abstract":"Abstract Sediment concentration (SC) monitoring has always been a pressing issue in water resource management, as many existing instruments still face challenges in accurately measuring due to environmental factors and instrument limitations. A robust technology is worth presenting to apply in the field site. This study firstly uses mean-absolute-error (MAE), root-mean-square error (RMSE), correlation coefficient (CC), and Nash–Sutcliffe efficiency coefficient (NSE) to describe the performance of the proposed convolutional neural network (CNN). Moreover, adapting the ensemble learning concept to compare the multiple machine learning (ML) approaches, the CNN presents the highest predicted accuracy, 91%, better than SVM (79%), VGG19 (63%) and ResNet50 (35%). As a result, the proposed CNN framework can appropriately apply the monitoring needs. The primary purpose is to develop a simple, accurate, and stable SC monitoring technology. Instead of some complex architectures, a simple and small neural network is adopted to implement real-time application (RTA). Via our design, such a traditional but critical issue can be improved to a new state. For example, by incorporating the concept of the Internet of Things (IoT) with our design, the distributed computing system for large-scale environmental monitoring can be realized quickly and easily.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":"68 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136376771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ting Zhang, Yi Li, Jianzhu Li, Zhixia Li, Congmei Wang, Jin Liu
The temporal and spatial resolutions of rainfall data directly affect the accuracy of hydrological simulation. Weather radar has been used in business in China, but the uncertainty of data is large. At present, research on radar data and fusion in small and medium-sized basins in China is very weak. In this paper, taking the Duanzhuang watershed as an example, based on station data, Shijiazhuang's radar data are preprocessed, optimized and fused. Eleven rainfall events are selected for fusion by three methods and quality evaluation, and three flood simulations are used to test their effect. The results show that preprocessing and initial optimization have poor effects on radar data improvement. The rainfall proportional coefficient fusion method performs best in rainfall spatial estimation, where the R2 values of the three inspection stations are increased to 0.51, 0.78 and 0.82. Three fusion datasets in the peak flow and flood volume of flood simulation perform better than station data. For example, in the No.20210721 flood, the NSE of the three fusion data increased by 39, 30 and 48%. This shows that the fusion method can effectively improve the data accuracy of radar and can obtain high temporal and spatial resolution rainfall data.
{"title":"Quantitative estimation and fusion optimization of radar rainfall in the Duanzhuang watershed at the eastern foot of the Taihang Mountains","authors":"Ting Zhang, Yi Li, Jianzhu Li, Zhixia Li, Congmei Wang, Jin Liu","doi":"10.2166/hydro.2023.058","DOIUrl":"https://doi.org/10.2166/hydro.2023.058","url":null,"abstract":"The temporal and spatial resolutions of rainfall data directly affect the accuracy of hydrological simulation. Weather radar has been used in business in China, but the uncertainty of data is large. At present, research on radar data and fusion in small and medium-sized basins in China is very weak. In this paper, taking the Duanzhuang watershed as an example, based on station data, Shijiazhuang's radar data are preprocessed, optimized and fused. Eleven rainfall events are selected for fusion by three methods and quality evaluation, and three flood simulations are used to test their effect. The results show that preprocessing and initial optimization have poor effects on radar data improvement. The rainfall proportional coefficient fusion method performs best in rainfall spatial estimation, where the R2 values of the three inspection stations are increased to 0.51, 0.78 and 0.82. Three fusion datasets in the peak flow and flood volume of flood simulation perform better than station data. For example, in the No.20210721 flood, the NSE of the three fusion data increased by 39, 30 and 48%. This shows that the fusion method can effectively improve the data accuracy of radar and can obtain high temporal and spatial resolution rainfall data.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":"2 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136376820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lihu Wang, Xuemei Liu, Yang Liu, Hairui Li, Jiaqi Liu
Abstract The emergency plans for water diversion projects suffer from weak knowledge correlation, inadequate timeliness, and insufficient support for intelligent decision-making. This study incorporates knowledge graph technology to enable intelligent recommendations for emergency plans in water diversion projects. By employing pre-trained language models (PTMs) with entity masking, the model's ability to recognize domain-specific entities is enhanced. By leveraging matrix-based two-dimensional transformations and feature recombination, an interactive convolutional neural network (ICNN) is constructed to enhance the processing capability of complex relationships. By integrating PTM with ICNN, a PTM–ICNN method for joint extraction of emergency entity relationships is constructed. By utilizing the Neo4j graph database to store emergency entity relationships, an emergency knowledge graph is constructed. By employing the mutual information criterion, intelligent retrieval and recommendation of emergency plans are achieved. The results demonstrate that the proposed approach achieves high extraction accuracy (F1 score of 91.33%) and provides reliable recommendations for emergency plans. This study can significantly enhance the level of intelligent emergency management in water diversion projects, thereby mitigating the impact of unforeseen events on engineering safety.
{"title":"Knowledge-driven intelligent recommendation method for emergency plans in water diversion projects","authors":"Lihu Wang, Xuemei Liu, Yang Liu, Hairui Li, Jiaqi Liu","doi":"10.2166/hydro.2023.251","DOIUrl":"https://doi.org/10.2166/hydro.2023.251","url":null,"abstract":"Abstract The emergency plans for water diversion projects suffer from weak knowledge correlation, inadequate timeliness, and insufficient support for intelligent decision-making. This study incorporates knowledge graph technology to enable intelligent recommendations for emergency plans in water diversion projects. By employing pre-trained language models (PTMs) with entity masking, the model's ability to recognize domain-specific entities is enhanced. By leveraging matrix-based two-dimensional transformations and feature recombination, an interactive convolutional neural network (ICNN) is constructed to enhance the processing capability of complex relationships. By integrating PTM with ICNN, a PTM–ICNN method for joint extraction of emergency entity relationships is constructed. By utilizing the Neo4j graph database to store emergency entity relationships, an emergency knowledge graph is constructed. By employing the mutual information criterion, intelligent retrieval and recommendation of emergency plans are achieved. The results demonstrate that the proposed approach achieves high extraction accuracy (F1 score of 91.33%) and provides reliable recommendations for emergency plans. This study can significantly enhance the level of intelligent emergency management in water diversion projects, thereby mitigating the impact of unforeseen events on engineering safety.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135168283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kegong Diao, Michael Emmerich, Jacob Lan, Iryna Yevseyeva, Robert Sitzenfrei
Abstract This paper introduces a multi-objective optimisation approach for the challenging problem of efficient sensor placement in water distribution networks for contamination detection. An important question is how to identify the minimal number of required sensors without losing the capacity to monitor the system as a whole. In this study, we adapted the NSGA-II multi-objective optimisation method by applying centrality mutation. The approach, with two objectives, namely the minimisation of Expected Time of Detection and maximisation of Detection Network Coverage (which computes the number of detected water contamination events), is tested on a moderate-sized benchmark problem (129 nodes). The resulting Pareto front shows that detection network coverage can improve dramatically by deploying only a few sensors (e.g. increase from one sensor to three sensors). However, after reaching a certain number of sensors (e.g. 20 sensors), the effectiveness of further increasing the number of sensors is not apparent. Further, the results confirm that 40–45 sensors (i.e. 31 − 35% of the total number of nodes) will be sufficient for fully monitoring the benchmark network, i.e. for detection of any contaminant intrusion event no matter where it appears in the network.
{"title":"Sensor placement in water distribution networks using centrality-guided multi-objective optimisation","authors":"Kegong Diao, Michael Emmerich, Jacob Lan, Iryna Yevseyeva, Robert Sitzenfrei","doi":"10.2166/hydro.2023.057","DOIUrl":"https://doi.org/10.2166/hydro.2023.057","url":null,"abstract":"Abstract This paper introduces a multi-objective optimisation approach for the challenging problem of efficient sensor placement in water distribution networks for contamination detection. An important question is how to identify the minimal number of required sensors without losing the capacity to monitor the system as a whole. In this study, we adapted the NSGA-II multi-objective optimisation method by applying centrality mutation. The approach, with two objectives, namely the minimisation of Expected Time of Detection and maximisation of Detection Network Coverage (which computes the number of detected water contamination events), is tested on a moderate-sized benchmark problem (129 nodes). The resulting Pareto front shows that detection network coverage can improve dramatically by deploying only a few sensors (e.g. increase from one sensor to three sensors). However, after reaching a certain number of sensors (e.g. 20 sensors), the effectiveness of further increasing the number of sensors is not apparent. Further, the results confirm that 40–45 sensors (i.e. 31 − 35% of the total number of nodes) will be sufficient for fully monitoring the benchmark network, i.e. for detection of any contaminant intrusion event no matter where it appears in the network.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135273246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bulat Kerimov, Roberto Bentivoglio, Alexander Garzón, Elvin Isufi, Franz Tscheikner-Gratl, David Bernhard Steffelbauer, Riccardo Taormina
Abstract Metamodels accurately reproduce the output of physics-based hydraulic models with a significant reduction in simulation times. They are widely employed in water distribution system (WDS) analysis since they enable computationally expensive applications in the design, control, and optimisation of water networks. Recent machine-learning-based metamodels grant improved fidelity and speed; however, they are only applicable to the water network they were trained on. To address this issue, we investigate graph neural networks (GNNs) as metamodels for WDSs. GNNs leverage the networked structure of WDS by learning shared coefficients and thus offering the potential of transferability. This work evaluates the suitability of GNNs as metamodels for estimating nodal pressures in steady-state EPANET simulations. We first compare the effectiveness of GNN metamodels against multi-layer perceptrons (MLPs) on several benchmark WDSs. Then, we explore the transferability of GNNs by training them concurrently on multiple WDSs. For each configuration, we calculate model accuracy and speedups with respect to the original numerical model. GNNs perform similarly to MLPs in terms of accuracy and take longer to execute but may still provide substantial speedup. Our preliminary results indicate that GNNs can learn shared representations across networks, although assessing the feasibility of truly general metamodels requires further work.
{"title":"Assessing the performances and transferability of graph neural network metamodels for water distribution systems","authors":"Bulat Kerimov, Roberto Bentivoglio, Alexander Garzón, Elvin Isufi, Franz Tscheikner-Gratl, David Bernhard Steffelbauer, Riccardo Taormina","doi":"10.2166/hydro.2023.031","DOIUrl":"https://doi.org/10.2166/hydro.2023.031","url":null,"abstract":"Abstract Metamodels accurately reproduce the output of physics-based hydraulic models with a significant reduction in simulation times. They are widely employed in water distribution system (WDS) analysis since they enable computationally expensive applications in the design, control, and optimisation of water networks. Recent machine-learning-based metamodels grant improved fidelity and speed; however, they are only applicable to the water network they were trained on. To address this issue, we investigate graph neural networks (GNNs) as metamodels for WDSs. GNNs leverage the networked structure of WDS by learning shared coefficients and thus offering the potential of transferability. This work evaluates the suitability of GNNs as metamodels for estimating nodal pressures in steady-state EPANET simulations. We first compare the effectiveness of GNN metamodels against multi-layer perceptrons (MLPs) on several benchmark WDSs. Then, we explore the transferability of GNNs by training them concurrently on multiple WDSs. For each configuration, we calculate model accuracy and speedups with respect to the original numerical model. GNNs perform similarly to MLPs in terms of accuracy and take longer to execute but may still provide substantial speedup. Our preliminary results indicate that GNNs can learn shared representations across networks, although assessing the feasibility of truly general metamodels requires further work.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135994844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Syed Zohaib Hassan, Peng Patrick Sun, Mert Gokgoz, Jiannan Chen, Debra Reinhart, Sarah Gustitus-Graham
Abstract Municipal solid waste (MSW) landfills need regular monitoring to ensure proper operations and meet environmental protection requirements. One requirement is to monitor landfill gas emissions from the landfill cover while another requirement is to monitor the potential settlement and damage to MSW landfill covers. Current surveying methods on a landfill cover are time- and labor-intensive and have limited spatial coverage. Landfill operators and researchers have developed unmanned aerial vehicle (UAV)-based monitoring over recent years; however, UAV-based automatic detection of water ponding in landfills has not been studied. Hence, this study proposes a UAV-based approach to monitor landfills and detect water ponding issues on covers by using multimodal sensor fusion. Data acquired from sensors mounted on a UAV were combined, leading to the creation of a ponding index (PI). This index was used to detect potential ponding sites or areas of topographical depression. The proposed approach has been applied in a case study of a closed MSW landfill before and after Hurricane Ian. A comparison between the generated PI map and a manual survey revealed a satisfactory performance with an IoU score of 70.74%. Hence, the utilization of UAV-based data fusing and the developed PI offers efficient identification of potential ponding areas.
{"title":"UAV-based approach for municipal solid waste landfill monitoring and water ponding issue detection using sensor fusion","authors":"Syed Zohaib Hassan, Peng Patrick Sun, Mert Gokgoz, Jiannan Chen, Debra Reinhart, Sarah Gustitus-Graham","doi":"10.2166/hydro.2023.195","DOIUrl":"https://doi.org/10.2166/hydro.2023.195","url":null,"abstract":"Abstract Municipal solid waste (MSW) landfills need regular monitoring to ensure proper operations and meet environmental protection requirements. One requirement is to monitor landfill gas emissions from the landfill cover while another requirement is to monitor the potential settlement and damage to MSW landfill covers. Current surveying methods on a landfill cover are time- and labor-intensive and have limited spatial coverage. Landfill operators and researchers have developed unmanned aerial vehicle (UAV)-based monitoring over recent years; however, UAV-based automatic detection of water ponding in landfills has not been studied. Hence, this study proposes a UAV-based approach to monitor landfills and detect water ponding issues on covers by using multimodal sensor fusion. Data acquired from sensors mounted on a UAV were combined, leading to the creation of a ponding index (PI). This index was used to detect potential ponding sites or areas of topographical depression. The proposed approach has been applied in a case study of a closed MSW landfill before and after Hurricane Ian. A comparison between the generated PI map and a manual survey revealed a satisfactory performance with an IoU score of 70.74%. Hence, the utilization of UAV-based data fusing and the developed PI offers efficient identification of potential ponding areas.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136294775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract This research introduces a novel nonlinear Muskingum model for river flood routing, aiming to enhance accuracy in modeling. It integrates lateral inflows using the Whale Optimization Algorithm (WOA) and employs a distributed Muskingum model, dividing river reaches into smaller intervals for precise calculations. The primary goal is to minimize the Sum of Square Errors (SSE) between the observed and modeled outflows. Our methodology is applied to six distinct flood hydrographs, revealing its versatility and efficacy. For Lawler's and Dinavar's flood data, the single-reach Muskingum model outperforms multi-reach versions, demonstrating its effectiveness in handling lateral inflows. For Lawler's data, the single-reach model (NR = 1) yields optimal parameters of K = 0.392, x = 0.027, m = 1.511, and β = 0.010, delivering superior results. Conversely, when fitting flood data from Wilson, Wye, Linsley, and Viessman and Lewis, the multi-reach Muskingum model exhibits better overall performance. Remarkably, the model excels with the Viessman and Lewis flood data, especially with two reaches (NR = 2), achieving a 21.6% SSE improvement while employing the same parameter set. This research represents a significant advancement in flood modeling, offering heightened accuracy and adaptability in river flood routing.
摘要为了提高模型的准确性，提出了一种新的非线性河流洪水路径模型。它使用鲸鱼优化算法(WOA)集成横向流入，并采用分布式Muskingum模型，将河流划分为更小的间隔以进行精确计算。主要目标是最小化观测到的和模拟流出之间的平方和误差(SSE)。我们的方法应用于六个不同的洪水水文，揭示了它的多功能性和有效性。对于Lawler和Dinavar的洪水数据，单河段Muskingum模型优于多河段模型，证明了其在处理横向流入方面的有效性。对于Lawler的数据，单步模型(NR = 1)的最优参数为K = 0.392, x = 0.027, m = 1.511， β = 0.010，具有较好的效果。相反，当拟合Wilson、Wye、Linsley、Viessman和Lewis的洪水数据时，多河段Muskingum模型表现出更好的整体性能。值得注意的是，该模型在Viessman和Lewis洪水数据上表现出色，特别是在两条河段(NR = 2)时，在使用相同参数集的情况下，SSE提高了21.6%。这项研究代表了洪水建模的重大进步，提高了河流洪水路径的准确性和适应性。
{"title":"Distributed Muskingum model with a Whale Optimization Algorithm for river flood routing","authors":"Vida Atashi, Reza Barati, Yeo Howe Lim","doi":"10.2166/hydro.2023.029","DOIUrl":"https://doi.org/10.2166/hydro.2023.029","url":null,"abstract":"Abstract This research introduces a novel nonlinear Muskingum model for river flood routing, aiming to enhance accuracy in modeling. It integrates lateral inflows using the Whale Optimization Algorithm (WOA) and employs a distributed Muskingum model, dividing river reaches into smaller intervals for precise calculations. The primary goal is to minimize the Sum of Square Errors (SSE) between the observed and modeled outflows. Our methodology is applied to six distinct flood hydrographs, revealing its versatility and efficacy. For Lawler's and Dinavar's flood data, the single-reach Muskingum model outperforms multi-reach versions, demonstrating its effectiveness in handling lateral inflows. For Lawler's data, the single-reach model (NR = 1) yields optimal parameters of K = 0.392, x = 0.027, m = 1.511, and β = 0.010, delivering superior results. Conversely, when fitting flood data from Wilson, Wye, Linsley, and Viessman and Lewis, the multi-reach Muskingum model exhibits better overall performance. Remarkably, the model excels with the Viessman and Lewis flood data, especially with two reaches (NR = 2), achieving a 21.6% SSE improvement while employing the same parameter set. This research represents a significant advancement in flood modeling, offering heightened accuracy and adaptability in river flood routing.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135094674","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","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：