Thanks to the rapid development of internet technology and computer hardware, it is now possible to use web services to provide visual simulations of flow field calculation results. Visualization technology can display complex water flow data and the laws that govern water flow through graphical means, and can be used to solve scientific and engineering problems related to water conservancy. In this study, we developed a platform for visualizing flow in a watershed based on a Cesium rendering framework with Browser/Server (B/S) architecture that used isosurface, particles, texture-based, and dynamic flow visualization techniques to visualize scalar field, vector field, and dynamic flow field data. Furthermore, our performance test results indicate that the rendering performance meets the practical application requirements for visualizing large-scale flow fields by employing frame interpolation and viewpoint-based dynamic rendering techniques. The results from testing the water flow visualization platform in the Beijiang River Basin, Guangdong Province, China, demonstrated that the platform performed well on different devices and that the running frame rate reached 50–60 fps. These findings can be used to guide further development and applications of web-side flow field visualization technology.
{"title":"Developing and testing a web-based platform for visualizing flow in a watershed","authors":"Jun Hou, Shang-hong Zhang, Haiyun Tang, Yang Zhou","doi":"10.2166/hydro.2023.155","DOIUrl":"https://doi.org/10.2166/hydro.2023.155","url":null,"abstract":"\u0000 \u0000 Thanks to the rapid development of internet technology and computer hardware, it is now possible to use web services to provide visual simulations of flow field calculation results. Visualization technology can display complex water flow data and the laws that govern water flow through graphical means, and can be used to solve scientific and engineering problems related to water conservancy. In this study, we developed a platform for visualizing flow in a watershed based on a Cesium rendering framework with Browser/Server (B/S) architecture that used isosurface, particles, texture-based, and dynamic flow visualization techniques to visualize scalar field, vector field, and dynamic flow field data. Furthermore, our performance test results indicate that the rendering performance meets the practical application requirements for visualizing large-scale flow fields by employing frame interpolation and viewpoint-based dynamic rendering techniques. The results from testing the water flow visualization platform in the Beijiang River Basin, Guangdong Province, China, demonstrated that the platform performed well on different devices and that the running frame rate reached 50–60 fps. These findings can be used to guide further development and applications of web-side flow field visualization technology.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41742505","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}
N. Olsen, Subhojit Kadia, E. Pummer, G. Hillebrand
A new OpenFOAM solver has been developed for computing the spatial variation of particle concentrations in flowing water. The new solver was programmed in C ++ using OpenFOAM libraries, and the source code has been made openly available. The current article describes the coding of how the water flow and particle movements are computed. The solver is based on a Eulearian approach, where the particles are computed as concentrations in cells of a grid that resolves the computational domain. The Reynolds-averaged Navier–Stokes equations are solved by simpleFoam, using the k-ε turbulence model. The new solver uses a drift-flux approach to take the fall or rise velocity of the particles into account in a convection-diffusion equation. The model is therefore called sediDriftFoam. The results from the solver were tested on two cases with different types of particles. The first case was a sand trap with sand particles. The geometry was three-dimensional with a recirculation zone. The computed sediment concentrations in three vertical profiles compared well with earlier numerical studies and laboratory measurements. The second case was a straight channel flume with plastic particles that had a positive rise velocity. In this case, the results also compared well with the laboratory measurements.
{"title":"An OpenFOAM solver for computing suspended particles in water currents","authors":"N. Olsen, Subhojit Kadia, E. Pummer, G. Hillebrand","doi":"10.2166/hydro.2023.309","DOIUrl":"https://doi.org/10.2166/hydro.2023.309","url":null,"abstract":"\u0000 A new OpenFOAM solver has been developed for computing the spatial variation of particle concentrations in flowing water. The new solver was programmed in C ++ using OpenFOAM libraries, and the source code has been made openly available. The current article describes the coding of how the water flow and particle movements are computed. The solver is based on a Eulearian approach, where the particles are computed as concentrations in cells of a grid that resolves the computational domain. The Reynolds-averaged Navier–Stokes equations are solved by simpleFoam, using the k-ε turbulence model. The new solver uses a drift-flux approach to take the fall or rise velocity of the particles into account in a convection-diffusion equation. The model is therefore called sediDriftFoam. The results from the solver were tested on two cases with different types of particles. The first case was a sand trap with sand particles. The geometry was three-dimensional with a recirculation zone. The computed sediment concentrations in three vertical profiles compared well with earlier numerical studies and laboratory measurements. The second case was a straight channel flume with plastic particles that had a positive rise velocity. In this case, the results also compared well with the laboratory measurements.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41798823","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}
G. R. Abhijith, Maddukuri Naveen Naidu, Sriman Pankaj Boindala, A. Vasan, A. Ostfeld
A substantial number of water distribution systems (WDS) worldwide are operated as intermittent water supply (IWS) systems, delivering water to consumers in irregular and unreliable manners. The IWS consumers commonly adapt to flexible consumption behaviors characterized by storing the limited water available during shorter supply periods in intermediate storage facilities for subsequent usage during more extended nonsupply periods. Nevertheless, the impacts of such consumer behavior on the performance of IWS systems have not been adequately addressed. Toward this direction, this article presents a novel open-source Python-based simulation tool (EPyT-IWS) for WDS, virtually acting like an IWS modeling extension of EPANET 2.2. The applicability of EPyT-IWS was demonstrated by conducting hydraulic simulations of a typical WDS with representative IWS attributes. Different IWS operation cases were considered by varying the amount and consistency of the water availability to the consumers. EPyT-IWS outputs showed that domestic storing of water within underground tanks and subsequent pumping into overhead tanks allow consumers to cope with the intermittent water availability and suitably meet their demands. Besides the interval, the clock time of the water supply was predicted to influence IWS consumers’ ability to meet water demands.
{"title":"Analyzing the role of consumer behavior in coping with intermittent supply in water distribution systems","authors":"G. R. Abhijith, Maddukuri Naveen Naidu, Sriman Pankaj Boindala, A. Vasan, A. Ostfeld","doi":"10.2166/hydro.2023.022","DOIUrl":"https://doi.org/10.2166/hydro.2023.022","url":null,"abstract":"\u0000 \u0000 A substantial number of water distribution systems (WDS) worldwide are operated as intermittent water supply (IWS) systems, delivering water to consumers in irregular and unreliable manners. The IWS consumers commonly adapt to flexible consumption behaviors characterized by storing the limited water available during shorter supply periods in intermediate storage facilities for subsequent usage during more extended nonsupply periods. Nevertheless, the impacts of such consumer behavior on the performance of IWS systems have not been adequately addressed. Toward this direction, this article presents a novel open-source Python-based simulation tool (EPyT-IWS) for WDS, virtually acting like an IWS modeling extension of EPANET 2.2. The applicability of EPyT-IWS was demonstrated by conducting hydraulic simulations of a typical WDS with representative IWS attributes. Different IWS operation cases were considered by varying the amount and consistency of the water availability to the consumers. EPyT-IWS outputs showed that domestic storing of water within underground tanks and subsequent pumping into overhead tanks allow consumers to cope with the intermittent water availability and suitably meet their demands. Besides the interval, the clock time of the water supply was predicted to influence IWS consumers’ ability to meet water demands.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42483312","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}
Numerous studies on the pressure fluctuations and cavity volume variations of a transient cavitation flow in viscoelastic pipes are available in the literature. However, the effect of water temperature on the cavity volume and energy conversion has been studied less often. This paper employs the discrete vapor cavity model (DVCM) using quasi-steady friction and quasi-two-dimensional friction models to calculate the cavity volume for different water temperatures and investigates the effects of water temperature on the appearance of the first cavitation at the downstream valve, as well as on the pressure damping in a tank-piping-valve system using an integrated energy analysis approach. The results show that the differences between the pressure and energy variations of the transient cavitation flow simulated using different models were minimal under different water temperature conditions. Moreover, as the water temperature increased, the appearance time of the cavity is postponed, and the volume of the cavity decreases. The energy dissipation increases continuously with an increase in the volume of the cavitation and water temperature in viscoelastic pipes. This study provides valuable insights into the variation pattern of the cavity and the effect of vapor cavities on the rise and decay of the pipeline pressure in different situations.
{"title":"Energy analysis of transient flow with cavitation by considering the effect of water temperature in viscoelastic pipes","authors":"Q.-X. Sun, Fu-Gang Wang, Yuebin Wu, Ying Xu, Yingqi Hao","doi":"10.2166/hydro.2023.231","DOIUrl":"https://doi.org/10.2166/hydro.2023.231","url":null,"abstract":"\u0000 \u0000 Numerous studies on the pressure fluctuations and cavity volume variations of a transient cavitation flow in viscoelastic pipes are available in the literature. However, the effect of water temperature on the cavity volume and energy conversion has been studied less often. This paper employs the discrete vapor cavity model (DVCM) using quasi-steady friction and quasi-two-dimensional friction models to calculate the cavity volume for different water temperatures and investigates the effects of water temperature on the appearance of the first cavitation at the downstream valve, as well as on the pressure damping in a tank-piping-valve system using an integrated energy analysis approach. The results show that the differences between the pressure and energy variations of the transient cavitation flow simulated using different models were minimal under different water temperature conditions. Moreover, as the water temperature increased, the appearance time of the cavity is postponed, and the volume of the cavity decreases. The energy dissipation increases continuously with an increase in the volume of the cavitation and water temperature in viscoelastic pipes. This study provides valuable insights into the variation pattern of the cavity and the effect of vapor cavities on the rise and decay of the pipeline pressure in different situations.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45524987","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}
Woon Yang Tan, S. Lai, K. Pavitra, F. Teo, A. El-shafie
Water security and urban flooding have become major sustainability issues. This paper presents a novel method to introduce rates of change as the state-of-the-art approach in artificial intelligence model development for sustainability agenda. Multi-layer perceptron (MLP) and deep learning long short-term memory (LSTM) models were considered for flood forecasting. Historical rainfall data from 2008 to 2021 at 11 telemetry stations were obtained to predict flow at the confluence between Klang River and Ampang River. The initial results of MLP yielded poor performance beneath normal expectations, which was R = 0.4465, MAE = 3.7135, NSE = 0.1994 and RMSE = 8.8556. Meanwhile, the LSTM model generated a 45% improvement in its R-value up to 0.9055. Detailed investigations found that the redundancy of data input that yielded multiple target values had distorted the model performance. Qt was introduced into input parameters to solve this issue, while Qt+0.5 was the target value. A significant improvement in the results was detected with R = 0.9359, MAE = 0.7722, NSE = 0.8756 and RMSE = 3.4911. When the rates of change were employed, an impressive improvement was seen for the plot of actual vs. forecasted flow. Findings showed that the rates of change could reduce forecast errors and were helpful as an additional layer of early flood detection.
{"title":"Deep learning model on rates of change for multi-step ahead streamflow forecasting","authors":"Woon Yang Tan, S. Lai, K. Pavitra, F. Teo, A. El-shafie","doi":"10.2166/hydro.2023.001","DOIUrl":"https://doi.org/10.2166/hydro.2023.001","url":null,"abstract":"\u0000 \u0000 Water security and urban flooding have become major sustainability issues. This paper presents a novel method to introduce rates of change as the state-of-the-art approach in artificial intelligence model development for sustainability agenda. Multi-layer perceptron (MLP) and deep learning long short-term memory (LSTM) models were considered for flood forecasting. Historical rainfall data from 2008 to 2021 at 11 telemetry stations were obtained to predict flow at the confluence between Klang River and Ampang River. The initial results of MLP yielded poor performance beneath normal expectations, which was R = 0.4465, MAE = 3.7135, NSE = 0.1994 and RMSE = 8.8556. Meanwhile, the LSTM model generated a 45% improvement in its R-value up to 0.9055. Detailed investigations found that the redundancy of data input that yielded multiple target values had distorted the model performance. Qt was introduced into input parameters to solve this issue, while Qt+0.5 was the target value. A significant improvement in the results was detected with R = 0.9359, MAE = 0.7722, NSE = 0.8756 and RMSE = 3.4911. When the rates of change were employed, an impressive improvement was seen for the plot of actual vs. forecasted flow. Findings showed that the rates of change could reduce forecast errors and were helpful as an additional layer of early flood detection.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44893593","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}
The Life Safety Model (LSM) is an agent-based model which assists with emergency planning and risk assessments for floods and dam failures by providing estimates of fatalities and evacuation times. The LSM represents the interactions of agents (i.e. people, vehicles, and buildings) with the floodwater. The LSM helps to increase the accuracy of estimates of loss of life and evacuation times for these events by taking into account a number of parameters which are not described in empirical models, such as the people's characteristics (e.g. age and gender), building construction types, and the road network. The LSM has been applied to three historic flood-related disasters: the 1953 coastal floods, in the UK; the 1959 Malpasset Dam failure, in France; the 2019 Brumadinho tailings dam disaster, in Brazil. These illustrate how the LSM has been verified and improvements to evacuation routes, early warnings, and the refuge locations could have reduced the number of fatalities. The value of using the LSM is not to calculate the ‘exact’ number of flood deaths or evacuation times, but to assess if emergency management interventions can significantly reduce them. The LSM can also be used to assess whether the societal risk posed by dams and flood defences is ‘acceptable’.
{"title":"Development of an agent-based model to improve emergency planning for floods and dam failures","authors":"D. Lumbroso, M. Davison, M. Wetton","doi":"10.2166/hydro.2023.194","DOIUrl":"https://doi.org/10.2166/hydro.2023.194","url":null,"abstract":"\u0000 \u0000 The Life Safety Model (LSM) is an agent-based model which assists with emergency planning and risk assessments for floods and dam failures by providing estimates of fatalities and evacuation times. The LSM represents the interactions of agents (i.e. people, vehicles, and buildings) with the floodwater. The LSM helps to increase the accuracy of estimates of loss of life and evacuation times for these events by taking into account a number of parameters which are not described in empirical models, such as the people's characteristics (e.g. age and gender), building construction types, and the road network. The LSM has been applied to three historic flood-related disasters: the 1953 coastal floods, in the UK; the 1959 Malpasset Dam failure, in France; the 2019 Brumadinho tailings dam disaster, in Brazil. These illustrate how the LSM has been verified and improvements to evacuation routes, early warnings, and the refuge locations could have reduced the number of fatalities. The value of using the LSM is not to calculate the ‘exact’ number of flood deaths or evacuation times, but to assess if emergency management interventions can significantly reduce them. The LSM can also be used to assess whether the societal risk posed by dams and flood defences is ‘acceptable’.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42443415","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}
Michele Magni, E. Sutanudjaja, Youchen Shen, D. Karssenberg
We present a novel hybrid framework that incorporates information from the process-based global hydrological model (GHM) PCR-GLOBWB, to reduce prediction errors in streamflow simulations. In addition to catchment attributes and meteorological data, our methodology employs simulated streamflow and state variables from PCR-GLOBWB as predictors of observed river discharge. These outputs are used in a random forest, trained on a global database of streamflow measurements, to improve estimates of simulated river discharge across the globe. PCR-GLOBWB was run for the years 1979–2019 at 30 arcmin and its inputs and outputs were upscaled from daily to monthly time steps. A single random forest model was trained with these state variables, meteorological data and catchment attributes, as predictors of observed streamflow from 2,286 stations worldwide. Model performance was evaluated using Kling–Gupta efficiency (KGE). Results based on cross-validation show that the model is capable of discerning between a variety of hydroclimatic conditions and river flow dynamics, improving KGE of PCR-GLOBWB simulations at more than 80% of testing locations and increasing median KGE from −0.02 in uncalibrated runs to 0.52 after post-processing. Performance boosts are usually independent of the availability of streamflow data, making our method a potential candidate in addressing prediction in poorly gauged and ungauged basins.
{"title":"Global streamflow modelling using process-informed machine learning","authors":"Michele Magni, E. Sutanudjaja, Youchen Shen, D. Karssenberg","doi":"10.2166/hydro.2023.217","DOIUrl":"https://doi.org/10.2166/hydro.2023.217","url":null,"abstract":"\u0000 We present a novel hybrid framework that incorporates information from the process-based global hydrological model (GHM) PCR-GLOBWB, to reduce prediction errors in streamflow simulations. In addition to catchment attributes and meteorological data, our methodology employs simulated streamflow and state variables from PCR-GLOBWB as predictors of observed river discharge. These outputs are used in a random forest, trained on a global database of streamflow measurements, to improve estimates of simulated river discharge across the globe. PCR-GLOBWB was run for the years 1979–2019 at 30 arcmin and its inputs and outputs were upscaled from daily to monthly time steps. A single random forest model was trained with these state variables, meteorological data and catchment attributes, as predictors of observed streamflow from 2,286 stations worldwide. Model performance was evaluated using Kling–Gupta efficiency (KGE). Results based on cross-validation show that the model is capable of discerning between a variety of hydroclimatic conditions and river flow dynamics, improving KGE of PCR-GLOBWB simulations at more than 80% of testing locations and increasing median KGE from −0.02 in uncalibrated runs to 0.52 after post-processing. Performance boosts are usually independent of the availability of streamflow data, making our method a potential candidate in addressing prediction in poorly gauged and ungauged basins.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42236099","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}
Sajad Bijanvand, M. Mohammadi, A. Parsaie, Vishwanadham Mandala
In this research, the estimation of discharge in compound open channels with convergent and divergent floodplains using soft computing methods, including the neural fuzzy group method of data handling (NF-GMDH), support vector regression (SVR), and M5 tree algorithm were performed. For this purpose, the geometric and hydraulic characteristics of the flow, including relative roughness (ff), relative area (Ar), relative hydraulic radius (Rr), relative dimension of the flow aspects (δ*), relative width (β), relative flow depth (Dr), relative longitudinal distance (Xr), convergent or divergent angle (θ) of the floodplain and longitudinal slope (So) of the bed were used as input variables and discharge was considered as the target (output) variable. The results showed that the statistical indices of the NF-GMDH in the testing stage are RMSENF-GMDH = 0.004, R2NF-GMDH = 0.923 and in the same stage for SVR are RMSESVR= 0.002 and R2SVR = 0.941 and finally for M5 tree algorithm are RMSEM5 = 0.002, R2M5= 0.931. The evaluation of the structure of the M5 tree algorithm showed that the most effective parameters are ff, Dr, Rr, δ*, and θ which confirm the important parameters specified by MARS, GMDH, and GEP algorithms used by previous researchers.
{"title":"Modeling of Discharge in Compound open channels with Convergent and Divergent Floodplains Using Soft Computing Methods","authors":"Sajad Bijanvand, M. Mohammadi, A. Parsaie, Vishwanadham Mandala","doi":"10.2166/hydro.2023.014","DOIUrl":"https://doi.org/10.2166/hydro.2023.014","url":null,"abstract":"\u0000 In this research, the estimation of discharge in compound open channels with convergent and divergent floodplains using soft computing methods, including the neural fuzzy group method of data handling (NF-GMDH), support vector regression (SVR), and M5 tree algorithm were performed. For this purpose, the geometric and hydraulic characteristics of the flow, including relative roughness (ff), relative area (Ar), relative hydraulic radius (Rr), relative dimension of the flow aspects (δ*), relative width (β), relative flow depth (Dr), relative longitudinal distance (Xr), convergent or divergent angle (θ) of the floodplain and longitudinal slope (So) of the bed were used as input variables and discharge was considered as the target (output) variable. The results showed that the statistical indices of the NF-GMDH in the testing stage are RMSENF-GMDH = 0.004, R2NF-GMDH = 0.923 and in the same stage for SVR are RMSESVR= 0.002 and R2SVR = 0.941 and finally for M5 tree algorithm are RMSEM5 = 0.002, R2M5= 0.931. The evaluation of the structure of the M5 tree algorithm showed that the most effective parameters are ff, Dr, Rr, δ*, and θ which confirm the important parameters specified by MARS, GMDH, and GEP algorithms used by previous researchers.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48337505","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}
T. Lendzioch, J. Langhammer, Veethahavya Kootanoor Sheshadrivasan
This study uses the GRAINet convolutional neural networks (CNN) approach on unmanned aerial vehicles (UAVs) optical aerial imagery to analyze and predict grain size characteristics, specifically mean diameter (dm), along a gravel river point bar in Šumava National Park, Czechia. By employing a digital line sampling technique and manual annotations as ground truth, GRAINet offers an innovative solution for particle size analysis. Eight UAV overflights were conducted between 2014 and 2022 to monitor changes in grain size dm across the river point bar. The resulting dm prediction maps showed reasonably accurate results, with mean absolute error (MAE) values ranging from 1.9 to 4.4 cm in 10-fold cross-validations. Mean squared error (MSE) and root-mean-square error (RMSE) values varied from 7.13 to 27.24 cm and 2.49 to 4.07 cm, respectively. Most models underestimated grain size, with around 68.5% falling within 1σ and 90.75% falling within 2σ of the predicted GRAINet mean dm. However, deviations from actual grain sizes were observed, particularly for grains smaller than 5 cm. The study highlights the importance of a large manually labeled training dataset for the GRAINet approach, eliminating the need for user-parameter tuning and improving its suitability for large-scale applications.
{"title":"Automated mapping of the mean particle diameter characteristics from UAV-imagery using the CNN-based GRAINet model","authors":"T. Lendzioch, J. Langhammer, Veethahavya Kootanoor Sheshadrivasan","doi":"10.2166/hydro.2023.079","DOIUrl":"https://doi.org/10.2166/hydro.2023.079","url":null,"abstract":"\u0000 \u0000 This study uses the GRAINet convolutional neural networks (CNN) approach on unmanned aerial vehicles (UAVs) optical aerial imagery to analyze and predict grain size characteristics, specifically mean diameter (dm), along a gravel river point bar in Šumava National Park, Czechia. By employing a digital line sampling technique and manual annotations as ground truth, GRAINet offers an innovative solution for particle size analysis. Eight UAV overflights were conducted between 2014 and 2022 to monitor changes in grain size dm across the river point bar. The resulting dm prediction maps showed reasonably accurate results, with mean absolute error (MAE) values ranging from 1.9 to 4.4 cm in 10-fold cross-validations. Mean squared error (MSE) and root-mean-square error (RMSE) values varied from 7.13 to 27.24 cm and 2.49 to 4.07 cm, respectively. Most models underestimated grain size, with around 68.5% falling within 1σ and 90.75% falling within 2σ of the predicted GRAINet mean dm. However, deviations from actual grain sizes were observed, particularly for grains smaller than 5 cm. The study highlights the importance of a large manually labeled training dataset for the GRAINet approach, eliminating the need for user-parameter tuning and improving its suitability for large-scale applications.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42430563","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}
Paguédame Game, Mingyan Wang, P. Audra, P. Gourbesville
Nice Metropolis in Alpes Maritimes, France is prone to flood. The city is crossed by the Lower Paillons River (LPR). Its discharge for a return period of 100 years is estimated at 794 m3/s. Part of the river is covered by 2 km. In addition, there are two retention storages in the river bed and a floodable road tunnel on the left bank. Due to the increase in urban development, flood management is challenging. An existing decision support system (DSS), Aquavar, uses DHI Mike tools to reproduce runoff for the Lower Var River in the same region. To extend this system to the LPR and reinforce flood management, a new modelling tool adapted to the characteristics of the LPR is needed. Consequently, this research utilizes the DHI MIKEPLUS tool to develop a 1D–2D coupled model for real-time flood management. The results demonstrate that flood events like those in 2017 and 2019 were correctly reproduced. The linear regression R2 is above 0.8 for all stations. It was also estimated that the covered river (CR) should stay clean to avoid widespread flooding in the urban area. Overall, the model is useful for simulating flow in real time and can help sustain urban development.
{"title":"Flood modelling for a real-time decision support system of the covered Lower Paillons River, Nice, France","authors":"Paguédame Game, Mingyan Wang, P. Audra, P. Gourbesville","doi":"10.2166/hydro.2023.181","DOIUrl":"https://doi.org/10.2166/hydro.2023.181","url":null,"abstract":"\u0000 \u0000 Nice Metropolis in Alpes Maritimes, France is prone to flood. The city is crossed by the Lower Paillons River (LPR). Its discharge for a return period of 100 years is estimated at 794 m3/s. Part of the river is covered by 2 km. In addition, there are two retention storages in the river bed and a floodable road tunnel on the left bank. Due to the increase in urban development, flood management is challenging. An existing decision support system (DSS), Aquavar, uses DHI Mike tools to reproduce runoff for the Lower Var River in the same region. To extend this system to the LPR and reinforce flood management, a new modelling tool adapted to the characteristics of the LPR is needed. Consequently, this research utilizes the DHI MIKEPLUS tool to develop a 1D–2D coupled model for real-time flood management. The results demonstrate that flood events like those in 2017 and 2019 were correctly reproduced. The linear regression R2 is above 0.8 for all stations. It was also estimated that the covered river (CR) should stay clean to avoid widespread flooding in the urban area. Overall, the model is useful for simulating flow in real time and can help sustain urban development.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":" ","pages":""},"PeriodicalIF":2.7,"publicationDate":"2023-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44297230","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：