Mingyan Wang, Paguédame Game, Philippe Gourbesville
Abstract To achieve an integrated river basin management for the Cagne catchment (France) and better predict the flood, various modeling tools are integrated within a unified framework, forming a decision support system (DSS). In the paper, an integrated modeling approach employing deterministic distributed hydrological (MIKE SHE), hydraulic (MIKE 21 FM), and hydrogeological (FEFLOW) models is presented. The hydrological model was validated with recorded data and following a sensitivity analysis for optimizing grid resolution with 20 m. The hydraulic model based on MIKE 21 FM utilizes the results generated by the MIKE SHE model as boundary conditions, producing inundation maps for both normal and extreme periods. The hydrogeological model addresses the various complex relationships taking place within the catchment and was validated with piezometer data. The integration of these three models into a DSS provides a valuable tool for decision-makers to manage the Cagne catchment and the water-related issues more effectively during various hydrological situations. This comprehensive modeling framework underscores the importance of interdisciplinary approaches for addressing complex hydrological processes and contributes to improved flood management strategies in the catchment.
{"title":"Advancing integrated river basin management and flood forecasting in the Cagne catchment: a combined approach using deterministic distributed models","authors":"Mingyan Wang, Paguédame Game, Philippe Gourbesville","doi":"10.2166/hydro.2023.100","DOIUrl":"https://doi.org/10.2166/hydro.2023.100","url":null,"abstract":"Abstract To achieve an integrated river basin management for the Cagne catchment (France) and better predict the flood, various modeling tools are integrated within a unified framework, forming a decision support system (DSS). In the paper, an integrated modeling approach employing deterministic distributed hydrological (MIKE SHE), hydraulic (MIKE 21 FM), and hydrogeological (FEFLOW) models is presented. The hydrological model was validated with recorded data and following a sensitivity analysis for optimizing grid resolution with 20 m. The hydraulic model based on MIKE 21 FM utilizes the results generated by the MIKE SHE model as boundary conditions, producing inundation maps for both normal and extreme periods. The hydrogeological model addresses the various complex relationships taking place within the catchment and was validated with piezometer data. The integration of these three models into a DSS provides a valuable tool for decision-makers to manage the Cagne catchment and the water-related issues more effectively during various hydrological situations. This comprehensive modeling framework underscores the importance of interdisciplinary approaches for addressing complex hydrological processes and contributes to improved flood management strategies in the catchment.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135480473","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}
Nuno M. C. Martins, Dídia I. C. Covas, Silvia Meniconi, Caterina Capponi, Bruno Brunone
Abstract In this paper, an advanced three-dimensional (3D) computational fluid dynamics (CFD) model is used to analyse the steady-state hydrodynamics of laminar flow through an extended partial blockage (PB) in a pressurised pipe. PB corresponds to one of the main faults affecting pipelines. In fact, it reduces its carrying capacity with economic consequences, and as it does not give rise to any external evidence, its detection can be very challenging. The performance of the model is evaluated by comparing the numerical results with the available experimental data from the literature. Subsequently, the velocity and pressure distributions are analysed, and the main features of the flow field are described in terms of both local and global dimensionless parameters. Furthermore, the behaviour of the discharge coefficient is also investigated. The obtained results confirm that steady-state measurements can identify the presence of PB and follow its evolution over time but cannot detect its location and size. On the other hand, the location and severity of PBs can be provided by means of transient tests.
{"title":"Hydrodynamics of laminar pipe flow through an extended partial blockage by CFD","authors":"Nuno M. C. Martins, Dídia I. C. Covas, Silvia Meniconi, Caterina Capponi, Bruno Brunone","doi":"10.2166/hydro.2023.042","DOIUrl":"https://doi.org/10.2166/hydro.2023.042","url":null,"abstract":"Abstract In this paper, an advanced three-dimensional (3D) computational fluid dynamics (CFD) model is used to analyse the steady-state hydrodynamics of laminar flow through an extended partial blockage (PB) in a pressurised pipe. PB corresponds to one of the main faults affecting pipelines. In fact, it reduces its carrying capacity with economic consequences, and as it does not give rise to any external evidence, its detection can be very challenging. The performance of the model is evaluated by comparing the numerical results with the available experimental data from the literature. Subsequently, the velocity and pressure distributions are analysed, and the main features of the flow field are described in terms of both local and global dimensionless parameters. Furthermore, the behaviour of the discharge coefficient is also investigated. The obtained results confirm that steady-state measurements can identify the presence of PB and follow its evolution over time but cannot detect its location and size. On the other hand, the location and severity of PBs can be provided by means of transient tests.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135873769","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 study presents the development of a novel hybrid wind power generator–water distillation system with the objective of providing sustainable solutions for impoverished isolated communities facing limited resources. The advantage of the proposed system is its ability to operate day and night; therefore, it produces larger quantities of distilled water even on cloudy days with winds. The system comprises a Venturi tunnel integrated with a wind turbine, an attached impure water tank, and a condenser located at the end section. The accelerated airflow at the throat section serves two purposes: water evaporation from the tank and power generation through the wind turbine. The evaporated water is subsequently collected as the airflow decelerates and the pressure decreases along the diverging section. Theoretical and computational modelling is employed to design the system by examining air speed, area ratio, relative humidity, as well as air, and water temperatures. The system exhibits enhanced performance under warm and dry weather conditions, thereby optimizing its performance. Conversely, temperature and relative humidity do not affect power generation; it was increased by higher air speeds and larger area ratios. This data-driven approach ensures optimal design parameters are selected, aligning the system's capabilities with the specific freshwater demand.
{"title":"Modelling of a hybrid wind power generator–water distillation system using a Venturi tunnel","authors":"Malak I. Naji, M. A. Al-Nimr","doi":"10.2166/hydro.2023.269","DOIUrl":"https://doi.org/10.2166/hydro.2023.269","url":null,"abstract":"Abstract This study presents the development of a novel hybrid wind power generator–water distillation system with the objective of providing sustainable solutions for impoverished isolated communities facing limited resources. The advantage of the proposed system is its ability to operate day and night; therefore, it produces larger quantities of distilled water even on cloudy days with winds. The system comprises a Venturi tunnel integrated with a wind turbine, an attached impure water tank, and a condenser located at the end section. The accelerated airflow at the throat section serves two purposes: water evaporation from the tank and power generation through the wind turbine. The evaporated water is subsequently collected as the airflow decelerates and the pressure decreases along the diverging section. Theoretical and computational modelling is employed to design the system by examining air speed, area ratio, relative humidity, as well as air, and water temperatures. The system exhibits enhanced performance under warm and dry weather conditions, thereby optimizing its performance. Conversely, temperature and relative humidity do not affect power generation; it was increased by higher air speeds and larger area ratios. This data-driven approach ensures optimal design parameters are selected, aligning the system's capabilities with the specific freshwater demand.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135933094","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}
Drinking water utilities and commercial vendors are developing battery-powered autonomous robots for the internal inspection of pipelines. However, these robots require nearby charging stations next to the pipelines of the water distribution networks (WDN). This prompts practical questions about the minimal number of charging stations and robots required. To address the questions, an integer linear programming optimization is formulated, akin to set covering, based on the shortest path of the charging stations to each node along a pipeline. The optimization decisions revolve around designating nodes as charging stations, considering the maximum distance (δmax) at which a robot can cover a hard constraint. For optimal placement, two objective formulations are proposed: (i) minimize the total number of stations, representing total cost; and (ii) maximize the total redundancy of the system. The methodology is applied to three WDN topologies (i.e. Modena, Five Reservoirs, and E−Town). Results show the influence of topology on the total number of stations, the number of robots, and the redundancy of the charging stations network. A trade-off between δmax and total number of stations emphasizes robot battery capacity's significance mariocastrogama.
{"title":"Optimal charging station placement for autonomous robots in drinking water networks","authors":"Mario Castro-Gama, Yvonne Hassink-Mulder","doi":"10.2166/hydro.2023.040","DOIUrl":"https://doi.org/10.2166/hydro.2023.040","url":null,"abstract":"Drinking water utilities and commercial vendors are developing battery-powered autonomous robots for the internal inspection of pipelines. However, these robots require nearby charging stations next to the pipelines of the water distribution networks (WDN). This prompts practical questions about the minimal number of charging stations and robots required. To address the questions, an integer linear programming optimization is formulated, akin to set covering, based on the shortest path of the charging stations to each node along a pipeline. The optimization decisions revolve around designating nodes as charging stations, considering the maximum distance (δmax) at which a robot can cover a hard constraint. For optimal placement, two objective formulations are proposed: (i) minimize the total number of stations, representing total cost; and (ii) maximize the total redundancy of the system. The methodology is applied to three WDN topologies (i.e. Modena, Five Reservoirs, and E−Town). Results show the influence of topology on the total number of stations, the number of robots, and the redundancy of the charging stations network. A trade-off between δmax and total number of stations emphasizes robot battery capacity's significance mariocastrogama.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135973331","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}
Changli Li, Zheng Han, Yange Li, Ming Li, Weidong Wang, Ningsheng Chen, Guisheng Hu
Abstract The computational prediction of wave propagation in dam-break floods is a long-standing problem in hydrodynamics and hydrology. We show that a reservoir computing echo state network (RC-ESN) that is well-trained on a minimal amount of data can accurately predict the long-term dynamic behavior of a one-dimensional dam-break flood. We solve the de Saint-Venant equations for a one-dimensional dam-break flood scenario using the Lax–Wendroff numerical scheme and train the RC-ESN model. The results demonstrate that the RC-ESN model has good prediction ability, as it predicts wave propagation behavior 286 time-steps ahead with a root mean square error smaller than 0.01, outperforming the conventional long short-term memory (LSTM) model, which only predicts 81 time-steps ahead. We also provide a sensitivity analysis of prediction accuracy for RC-ESN's key parameters such as training set size, reservoir size, and spectral radius. Results indicate that the RC-ESN is less dependent on training set size, with a medium reservoir size of 1,200–2,600 sufficient. We confirm that the spectral radius has a complex influence on the prediction accuracy and currently recommend a smaller spectral radius. Even when the initial flow depth of the dam break is changed, the prediction horizon of RC-ESN remains greater than that of LSTM.
{"title":"Data-driven and echo state network-based prediction of wave propagation behavior in dam-break flood","authors":"Changli Li, Zheng Han, Yange Li, Ming Li, Weidong Wang, Ningsheng Chen, Guisheng Hu","doi":"10.2166/hydro.2023.035","DOIUrl":"https://doi.org/10.2166/hydro.2023.035","url":null,"abstract":"Abstract The computational prediction of wave propagation in dam-break floods is a long-standing problem in hydrodynamics and hydrology. We show that a reservoir computing echo state network (RC-ESN) that is well-trained on a minimal amount of data can accurately predict the long-term dynamic behavior of a one-dimensional dam-break flood. We solve the de Saint-Venant equations for a one-dimensional dam-break flood scenario using the Lax–Wendroff numerical scheme and train the RC-ESN model. The results demonstrate that the RC-ESN model has good prediction ability, as it predicts wave propagation behavior 286 time-steps ahead with a root mean square error smaller than 0.01, outperforming the conventional long short-term memory (LSTM) model, which only predicts 81 time-steps ahead. We also provide a sensitivity analysis of prediction accuracy for RC-ESN's key parameters such as training set size, reservoir size, and spectral radius. Results indicate that the RC-ESN is less dependent on training set size, with a medium reservoir size of 1,200–2,600 sufficient. We confirm that the spectral radius has a complex influence on the prediction accuracy and currently recommend a smaller spectral radius. Even when the initial flow depth of the dam break is changed, the prediction horizon of RC-ESN remains greater than that of LSTM.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135932824","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}
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":null,"pages":null},"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":null,"pages":null},"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":null,"pages":null},"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":null,"pages":null},"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":null,"pages":null},"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}
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：