This paper proposes a novel energy-balanced numerical scheme for the two-layer shallow water equations (2LSWEs) that accurately captures internal hydraulic jumps without introducing spurious oscillations. The proposed scheme overcomes the problem of post-shock oscillations in the 2LSWE, a phenomenon commonly observed in numerical solutions of non-linear hyperbolic systems when shock-capturing schemes are used. The approach involves reconstructing the internal momentum equation of 2LSWEs using the correct Hugoniot curve via a set of shock wave fixes originally developed for single-layer shallow water equations. The scheme successfully preserves all stationary solutions, making it highly suitable for simulations of real-life scenarios involving small perturbations of these conditions.
{"title":"Preserving stationary discontinuities in two-layer shallow water equations with a novel well-balanced approach","authors":"M. Akbari, B. Pirzadeh","doi":"10.2166/hydro.2023.312","DOIUrl":"https://doi.org/10.2166/hydro.2023.312","url":null,"abstract":"\u0000 \u0000 This paper proposes a novel energy-balanced numerical scheme for the two-layer shallow water equations (2LSWEs) that accurately captures internal hydraulic jumps without introducing spurious oscillations. The proposed scheme overcomes the problem of post-shock oscillations in the 2LSWE, a phenomenon commonly observed in numerical solutions of non-linear hyperbolic systems when shock-capturing schemes are used. The approach involves reconstructing the internal momentum equation of 2LSWEs using the correct Hugoniot curve via a set of shock wave fixes originally developed for single-layer shallow water equations. The scheme successfully preserves all stationary solutions, making it highly suitable for simulations of real-life scenarios involving small perturbations of these conditions.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45745887","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}
Amin Minaei, M. Hajibabaei, D. Savić, E. Creaco, R. Sitzenfrei
Water distribution networks (WDNs) with other infrastructures constitute a complex and interdependent multi-utility system. Considering interdependencies between WDNs and other urban infrastructures, this work proposes WDN intervention planning using a dynamic multi-utility approach to tackle the challenges of pressure deficits and cascading failures by the decoupling of different infrastructure systems. For this purpose, the study develops reliability indices representing the hydraulic and decoupled statuses of WDNs with neighbor infrastructures; the hydraulic reliability represents the robustness of the network against the water pressure deficit, and cascading reliability represents the extent to which WDN elements are decoupled from other assets elements. A multi-objective optimization algorithm is employed to develop rehabilitation strategies by introducing three approaches for WDN upgrade following a phased design and construction method. Evaluating intervention plans based on construction cost, reliability and cascade effects shows that, under budget limitation conditions, decoupling a WDN could significantly save the cascade cost such that 1% improvement in the decoupling reliability brings about 157.42 billion Rials cascade cost saving (present worth cost) to asset managers. On the other hand, the decoupled network is weak against hydraulic reliability which could make it by far less resilient network than the coupled network with around 75% hydraulic reliability difference.
{"title":"Optimal rehabilitation planning for aged water distribution mains considering cascading failures of interdependent infrastructure systems","authors":"Amin Minaei, M. Hajibabaei, D. Savić, E. Creaco, R. Sitzenfrei","doi":"10.2166/hydro.2023.165","DOIUrl":"https://doi.org/10.2166/hydro.2023.165","url":null,"abstract":"\u0000 \u0000 Water distribution networks (WDNs) with other infrastructures constitute a complex and interdependent multi-utility system. Considering interdependencies between WDNs and other urban infrastructures, this work proposes WDN intervention planning using a dynamic multi-utility approach to tackle the challenges of pressure deficits and cascading failures by the decoupling of different infrastructure systems. For this purpose, the study develops reliability indices representing the hydraulic and decoupled statuses of WDNs with neighbor infrastructures; the hydraulic reliability represents the robustness of the network against the water pressure deficit, and cascading reliability represents the extent to which WDN elements are decoupled from other assets elements. A multi-objective optimization algorithm is employed to develop rehabilitation strategies by introducing three approaches for WDN upgrade following a phased design and construction method. Evaluating intervention plans based on construction cost, reliability and cascade effects shows that, under budget limitation conditions, decoupling a WDN could significantly save the cascade cost such that 1% improvement in the decoupling reliability brings about 157.42 billion Rials cascade cost saving (present worth cost) to asset managers. On the other hand, the decoupled network is weak against hydraulic reliability which could make it by far less resilient network than the coupled network with around 75% hydraulic reliability difference.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44204596","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}
A static flood analysis (SFA) toolset is implemented with the purpose of performing simplified, event-based flood inundation modeling. The simulation process is divided into two steps: a topographic sink analysis of the terrain followed by flow accumulation (FA) of runoff volumes. Both procedures are coupled to account for sink storage effects. The sink analysis procedure determines the morphology of present sinks that are utilized during FA to calculate the sink storage by solving a mass balance, whereby inflows are captured in each sink according to their capacity and overflows are routed further downstream. Each sink is enriched with a set of hydrological attributes such as the total inflow, overflow, and flood depth. The flood depth is then utilized to determine the flood extent and flood depths of each sink. Two main options are made available for the FA procedure: either a single flow direction (SFD) or a novel formulation of the multiple flow direction (MFD) algorithm. Both methods were compared in terms of their accuracy with results from the TELEMAC-2D finite-volume solver for an urban inundation model. Both methods showed good agreement when compared with the validation results, with the MFD method performing marginally better than the SFD method.
{"title":"Coupled sink and flow accumulation analyses with single flow direction and multiple flow direction algorithms","authors":"Nicholas Ray Bowsher, H. Sieker, R. Hinkelmann","doi":"10.2166/hydro.2023.123","DOIUrl":"https://doi.org/10.2166/hydro.2023.123","url":null,"abstract":"\u0000 A static flood analysis (SFA) toolset is implemented with the purpose of performing simplified, event-based flood inundation modeling. The simulation process is divided into two steps: a topographic sink analysis of the terrain followed by flow accumulation (FA) of runoff volumes. Both procedures are coupled to account for sink storage effects. The sink analysis procedure determines the morphology of present sinks that are utilized during FA to calculate the sink storage by solving a mass balance, whereby inflows are captured in each sink according to their capacity and overflows are routed further downstream. Each sink is enriched with a set of hydrological attributes such as the total inflow, overflow, and flood depth. The flood depth is then utilized to determine the flood extent and flood depths of each sink. Two main options are made available for the FA procedure: either a single flow direction (SFD) or a novel formulation of the multiple flow direction (MFD) algorithm. Both methods were compared in terms of their accuracy with results from the TELEMAC-2D finite-volume solver for an urban inundation model. Both methods showed good agreement when compared with the validation results, with the MFD method performing marginally better than the SFD method.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47433450","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}
Lidia María Ortega Alvarado, M. Ramos, C. Enríquez, J. J. Cubillas
Water reservoirs are essential to ensure water supply to both the population and agriculture, especially in the Mediterranean basin. In some cases, analyses of water intended for human consumption have detected high levels of agrochemicals. Knowing the possible origin of these products is complex because there may be many agricultural plots within the reservoir basin. In this paper, we introduce a methodology to obtain the set of agricultural plots whose rainwater reaches the reservoir and in what proportion they affect the points where chemical analyses are performed. The method implements an extension of the D8 algorithm for the calculation of the drainage network, in which additional information about the land-use type of the area, as well as rainfall maps are also considered. In order to facilitate the user's analysis of the data, a plugin has been implemented in QGIS. This allows usability and the easy interaction with the visual information. The Rumblar reservoir basin, located in Andalusia (Spain) has been studied as a use case, surrounded by olive orchards. The result is a replicable methodology for any other water reservoir and for carrying out an individualized study of agricultural plots.
{"title":"Methodology for the study of the traceability of runoff water feeding reservoirs","authors":"Lidia María Ortega Alvarado, M. Ramos, C. Enríquez, J. J. Cubillas","doi":"10.2166/hydro.2023.092","DOIUrl":"https://doi.org/10.2166/hydro.2023.092","url":null,"abstract":"\u0000 \u0000 Water reservoirs are essential to ensure water supply to both the population and agriculture, especially in the Mediterranean basin. In some cases, analyses of water intended for human consumption have detected high levels of agrochemicals. Knowing the possible origin of these products is complex because there may be many agricultural plots within the reservoir basin. In this paper, we introduce a methodology to obtain the set of agricultural plots whose rainwater reaches the reservoir and in what proportion they affect the points where chemical analyses are performed. The method implements an extension of the D8 algorithm for the calculation of the drainage network, in which additional information about the land-use type of the area, as well as rainfall maps are also considered. In order to facilitate the user's analysis of the data, a plugin has been implemented in QGIS. This allows usability and the easy interaction with the visual information. The Rumblar reservoir basin, located in Andalusia (Spain) has been studied as a use case, surrounded by olive orchards. The result is a replicable methodology for any other water reservoir and for carrying out an individualized study of agricultural plots.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42885059","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}
Water–air two-phase flow has been the theoretical basis of traditional building drainage systems. However, with the popularization of water-saving devices, more research investigations need to be performed on the impact of solid waste on drainage systems. Through experiments under the solid waste scenario, the effects of drainage volume, diameter, and slope of the pipeline on the hydraulic performances of the horizontal main drain were investigated. The results showed that the depth ratio was mainly responsible for the change of positive pressure value in the horizontal main drain. The depth ratios and the positive pressure values were proportional to the drainage volumes and inversely proportional to the diameters and slopes of the pipeline. The final deposition distances of solid wastes in the horizontal main drain were proportional to the discharge volumes and the pipeline slopes. However, the effects of pipe diameters and flow rates on final deposition distances need to be considered in sections. The self-cleaning lengths based on clear water were 1.2–1.6 times the real final deposition distances of solid wastes.
{"title":"Experimental study on the hydraulic performance of the horizontal main drain of building drainage systems with solid waste","authors":"Ping Xu, Bin Fu, Yilin Song","doi":"10.2166/hydro.2023.056","DOIUrl":"https://doi.org/10.2166/hydro.2023.056","url":null,"abstract":"\u0000 \u0000 Water–air two-phase flow has been the theoretical basis of traditional building drainage systems. However, with the popularization of water-saving devices, more research investigations need to be performed on the impact of solid waste on drainage systems. Through experiments under the solid waste scenario, the effects of drainage volume, diameter, and slope of the pipeline on the hydraulic performances of the horizontal main drain were investigated. The results showed that the depth ratio was mainly responsible for the change of positive pressure value in the horizontal main drain. The depth ratios and the positive pressure values were proportional to the drainage volumes and inversely proportional to the diameters and slopes of the pipeline. The final deposition distances of solid wastes in the horizontal main drain were proportional to the discharge volumes and the pipeline slopes. However, the effects of pipe diameters and flow rates on final deposition distances need to be considered in sections. The self-cleaning lengths based on clear water were 1.2–1.6 times the real final deposition distances of solid wastes.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41896151","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}
D. Laucelli, Laura Enríquez, Andres David Ariza, F. Ciliberti, L. Berardi, O. Giustolisi
Digital transformation currently represents a clear opportunity for innovation in better management and planning of water distribution networks. Coupled with the increased investments in assets and the growing need of safe and high-quality water for the public, new opportunities are opening for digital tools that can help operators, consultant companies and researchers to support asset management tasks. This work presents the applications of a comprehensive digital water strategy on two real case studies with information provided by the Italian water company Acquedotto Pugliese. The proposed digital water strategy is based on the paradigm named digital water services. The strategy starts by improving the value of GIS and existing models' data. Then, advanced hydraulic modelling and topological analyses, using the complex network theory, along with artificial intelligence methodologies are the basis for the development of digital water services, which are the engineering apps that use the network digital twin to support the different stages of asset management, i.e., digital water strategy.
{"title":"A digital water strategy based on the digital water service concept to support asset management in a real system","authors":"D. Laucelli, Laura Enríquez, Andres David Ariza, F. Ciliberti, L. Berardi, O. Giustolisi","doi":"10.2166/hydro.2023.313","DOIUrl":"https://doi.org/10.2166/hydro.2023.313","url":null,"abstract":"\u0000 Digital transformation currently represents a clear opportunity for innovation in better management and planning of water distribution networks. Coupled with the increased investments in assets and the growing need of safe and high-quality water for the public, new opportunities are opening for digital tools that can help operators, consultant companies and researchers to support asset management tasks. This work presents the applications of a comprehensive digital water strategy on two real case studies with information provided by the Italian water company Acquedotto Pugliese. The proposed digital water strategy is based on the paradigm named digital water services. The strategy starts by improving the value of GIS and existing models' data. Then, advanced hydraulic modelling and topological analyses, using the complex network theory, along with artificial intelligence methodologies are the basis for the development of digital water services, which are the engineering apps that use the network digital twin to support the different stages of asset management, i.e., digital water strategy.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44749724","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}
Prinsi Singh, K. Prakash, Suraj Kumar, A. K. Kannaujiya, Tanuja Mohanty
Environmental catastrophes on a global scale have prompted a thorough evaluation of river morphology for sustainable basin development methods. Geomorphological investigations of river basins can provide significant information regarding quaternary tectonic deformations. The present investigation intends to reveal tectonic imprints in the Bearma River Basin (BRB). Bearma is a significant river in central India which flows through Vindhyan Supergroup, Lameta and Deccan Trap and contributes to developing the marginal Gangetic plain's architecture. The digital elevation data have been utilized to obtain the morphotectonic indices, tectonic activity classes and topographic characteristics. Bearma is an elongated basin with uplifted topography, continuously migrating channels, high hypsometric integral, and several stream length-gradient anomalies, indicating tectonic control over the basin. According to the tectonic activity index, 15.33, 38.99, and 46.55% areas of the BRB have high, moderate, or low tectonic activity, respectively. Topographical, lineament studies and field investigation show significant relief variation and prominence of tectonic activity over erosional and depositional processes in shaping the landscape towards the southern and south-eastern region of the BRB. Reactivation of basement faults and subsurface lineaments due to Himalayan tectonic and activity of the Son-Narmada North Fault are responsible for the recent deformation and development of the current hydrographic network.
{"title":"A synergistic approach to morphotectonic evolution for watershed management in the Bearma River Basin, Central India","authors":"Prinsi Singh, K. Prakash, Suraj Kumar, A. K. Kannaujiya, Tanuja Mohanty","doi":"10.2166/hydro.2023.055","DOIUrl":"https://doi.org/10.2166/hydro.2023.055","url":null,"abstract":"\u0000 Environmental catastrophes on a global scale have prompted a thorough evaluation of river morphology for sustainable basin development methods. Geomorphological investigations of river basins can provide significant information regarding quaternary tectonic deformations. The present investigation intends to reveal tectonic imprints in the Bearma River Basin (BRB). Bearma is a significant river in central India which flows through Vindhyan Supergroup, Lameta and Deccan Trap and contributes to developing the marginal Gangetic plain's architecture. The digital elevation data have been utilized to obtain the morphotectonic indices, tectonic activity classes and topographic characteristics. Bearma is an elongated basin with uplifted topography, continuously migrating channels, high hypsometric integral, and several stream length-gradient anomalies, indicating tectonic control over the basin. According to the tectonic activity index, 15.33, 38.99, and 46.55% areas of the BRB have high, moderate, or low tectonic activity, respectively. Topographical, lineament studies and field investigation show significant relief variation and prominence of tectonic activity over erosional and depositional processes in shaping the landscape towards the southern and south-eastern region of the BRB. Reactivation of basement faults and subsurface lineaments due to Himalayan tectonic and activity of the Son-Narmada North Fault are responsible for the recent deformation and development of the current hydrographic network.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44450481","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}
Cyanobacterial blooms are a persistent concern to water management and treatment, with blooms potentially causing the release of toxins and degrading water quality. However, previous models have not considered the zero inflation of cyanobacteria count data. Typically, a relatively large proportion of measured count data are zeros or non-detects of cyanobacteria, representing either no cyanobacteria was present or the cell number was too low to be detected. Commonly used Poisson and negative binomial models for count data underestimate the probability of zero data, making these models less reliable. This study proposes a Bayesian approach to fit the cyanobacteria abundance data with mixture models that handle zero-inflated data. Predictor variables considered included weather and water quality measures that can easily be obtained day-to-day. The optimal model (zero-inflated negative binomial) was used to predict cyanobacteria alert levels on a separate test set. The ability to predict narrow alert levels was limited, however, 76% accuracy was achieved in predicting cyanobacteria counts above or below 1,000 cells/mL. Parameter estimates were highly variable and demonstrated that complex and uncertain factors influence cyanobacteria count predictions. The modelling approach can be applied to a wide range of environmental problems where zero-inflated data is common.
{"title":"Predicting cyanobacteria abundance with Bayesian zero-inflated models","authors":"Yirao Zhang, Nicolás M. Peleato","doi":"10.2166/hydro.2023.229","DOIUrl":"https://doi.org/10.2166/hydro.2023.229","url":null,"abstract":"\u0000 Cyanobacterial blooms are a persistent concern to water management and treatment, with blooms potentially causing the release of toxins and degrading water quality. However, previous models have not considered the zero inflation of cyanobacteria count data. Typically, a relatively large proportion of measured count data are zeros or non-detects of cyanobacteria, representing either no cyanobacteria was present or the cell number was too low to be detected. Commonly used Poisson and negative binomial models for count data underestimate the probability of zero data, making these models less reliable. This study proposes a Bayesian approach to fit the cyanobacteria abundance data with mixture models that handle zero-inflated data. Predictor variables considered included weather and water quality measures that can easily be obtained day-to-day. The optimal model (zero-inflated negative binomial) was used to predict cyanobacteria alert levels on a separate test set. The ability to predict narrow alert levels was limited, however, 76% accuracy was achieved in predicting cyanobacteria counts above or below 1,000 cells/mL. Parameter estimates were highly variable and demonstrated that complex and uncertain factors influence cyanobacteria count predictions. The modelling approach can be applied to a wide range of environmental problems where zero-inflated data is common.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44396353","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}
X. Yan, Yan Wang, Boyuan Fan, A. Mohammadian, Jianwei Liu, Zuhao Zhu
Predicting the flow field around sluice gates is essential for controlling water levels and discharges in open channels and rivers. Smooth particle hydrodynamics (SPH) models can satisfactorily reproduce such free-surface flows, but they typically require long computational time and extensive computational resources. In this work, we propose a convolutional neural network (CNN) to predict the flow field around a sluice gate. A validated SPH model is used to carry out extensive simulations, and the generated data set is used to train and test CNN-based models. The results demonstrated that the developed CNN can accurately reproduce sluice gate flows, with R2 values exceeding 90% and significantly reducing the computational costs. Furthermore, various traditional machine learning algorithms comprising adaptive neuro-fuzzy inference system, genetic programing, multigene genetic programing, and one-dimensional CNN were also evaluated, and a comparison of the results showed that the developed CNN performed better than the traditional data-driven algorithms in predicting sluice gate flows. Therefore, the proposed method is a promising tool for providing rapid prediction of the spatial distribution of flow fields near the sluice, and potentially for predicting other spatially distributed hydrologic variables.
{"title":"Data-driven modeling of sluice gate flows using a convolutional neural network","authors":"X. Yan, Yan Wang, Boyuan Fan, A. Mohammadian, Jianwei Liu, Zuhao Zhu","doi":"10.2166/hydro.2023.200","DOIUrl":"https://doi.org/10.2166/hydro.2023.200","url":null,"abstract":"\u0000 Predicting the flow field around sluice gates is essential for controlling water levels and discharges in open channels and rivers. Smooth particle hydrodynamics (SPH) models can satisfactorily reproduce such free-surface flows, but they typically require long computational time and extensive computational resources. In this work, we propose a convolutional neural network (CNN) to predict the flow field around a sluice gate. A validated SPH model is used to carry out extensive simulations, and the generated data set is used to train and test CNN-based models. The results demonstrated that the developed CNN can accurately reproduce sluice gate flows, with R2 values exceeding 90% and significantly reducing the computational costs. Furthermore, various traditional machine learning algorithms comprising adaptive neuro-fuzzy inference system, genetic programing, multigene genetic programing, and one-dimensional CNN were also evaluated, and a comparison of the results showed that the developed CNN performed better than the traditional data-driven algorithms in predicting sluice gate flows. Therefore, the proposed method is a promising tool for providing rapid prediction of the spatial distribution of flow fields near the sluice, and potentially for predicting other spatially distributed hydrologic variables.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48117019","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}
Multi-source data-fusion approaches have been developed for estimating regional precipitation. However, studies considering the specific upper limits of the improved gridded rainfall data for different fusion approaches are limited. Here, the potential ranges of accuracy improvement for satellite and reanalysis rainfall products were addressed using various machine learning fusion approaches, including multivariate linear regression (MLR), feedforward neural network (FNN), random forest (RF), and long short-term memory (LSTM), over the Chinese mainland. All four fusion methods reduce errors in the original precipitation products. The upper limits of accuracy improvement in terms of correlation coefficient (CC) and root mean square error (RMSE) were 30.65 and 15.27%, respectively. M-RF showed the best average CC (0.828) and RMSE (4.62 mm/day) in the four seasons. LSTM performed the best under light rainfall events, whereas MLR and RF exhibited better performance under moderate and heavy rainfall events, respectively. Overall, these results serve as a basis for the fusion approach and technique selection, based on the comprehensive validation in different climate zones, altitudes, and seasons over the Chinese mainland.
{"title":"Accuracy of conventional fusion algorithms for precipitation estimates across the Chinese mainland","authors":"Qin Jiang, Zedong Fan, Yun Xu, Weiyue Li, Junhao Zhang","doi":"10.2166/hydro.2023.111","DOIUrl":"https://doi.org/10.2166/hydro.2023.111","url":null,"abstract":"\u0000 \u0000 Multi-source data-fusion approaches have been developed for estimating regional precipitation. However, studies considering the specific upper limits of the improved gridded rainfall data for different fusion approaches are limited. Here, the potential ranges of accuracy improvement for satellite and reanalysis rainfall products were addressed using various machine learning fusion approaches, including multivariate linear regression (MLR), feedforward neural network (FNN), random forest (RF), and long short-term memory (LSTM), over the Chinese mainland. All four fusion methods reduce errors in the original precipitation products. The upper limits of accuracy improvement in terms of correlation coefficient (CC) and root mean square error (RMSE) were 30.65 and 15.27%, respectively. M-RF showed the best average CC (0.828) and RMSE (4.62 mm/day) in the four seasons. LSTM performed the best under light rainfall events, whereas MLR and RF exhibited better performance under moderate and heavy rainfall events, respectively. Overall, these results serve as a basis for the fusion approach and technique selection, based on the comprehensive validation in different climate zones, altitudes, and seasons over the Chinese mainland.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47765550","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：