In this paper, the discharge coefficient prediction model for this structure in a subcritical flow regime is first established by extreme learning machine (ELM) and Bayesian network, and the model's performance is analyzed and verified in detail. In addition, the global sensitivity analysis method is introduced to the optimal prediction model to analyze the sensitivity for the dimensionless parameters affecting the discharge coefficient. The results show that the Bayesian extreme learning machine (BELM) can effectively predict the discharge coefficients of the symmetric stepped labyrinth side weir. The range of 95% confidence interval [−0.055,0.040] is also significantly smaller than that of the ELM ([−0.089,0.076]) and the Kernel extreme learning machine (KELM) ([−0.091,0.081]) at the testing stage. The dimensionless parameter ratio of upstream water depth of stepped labyrinth side weir p/y1 has the greatest effect on the discharge coefficient Cd, accounting for 55.57 and 54.17% under single action and other parameter interactions, respectively. Dimensionless step number bs/L has little effect on Cd, which can be ignored. Meanwhile, when the number of steps is less (N = 4) and the internal head angle is smaller (θ = 45°), a larger discharge coefficient value can be obtained.
{"title":"Analysis of discharge characteristics of a symmetrical stepped labyrinth side weir based on global sensitivity","authors":"Wuyi Wan, Guiying Shen, Shanshan Li, Abbas Parsaie, Yuhang Wang, Yu Zhou","doi":"10.2166/hydro.2023.260","DOIUrl":"https://doi.org/10.2166/hydro.2023.260","url":null,"abstract":"\u0000 In this paper, the discharge coefficient prediction model for this structure in a subcritical flow regime is first established by extreme learning machine (ELM) and Bayesian network, and the model's performance is analyzed and verified in detail. In addition, the global sensitivity analysis method is introduced to the optimal prediction model to analyze the sensitivity for the dimensionless parameters affecting the discharge coefficient. The results show that the Bayesian extreme learning machine (BELM) can effectively predict the discharge coefficients of the symmetric stepped labyrinth side weir. The range of 95% confidence interval [−0.055,0.040] is also significantly smaller than that of the ELM ([−0.089,0.076]) and the Kernel extreme learning machine (KELM) ([−0.091,0.081]) at the testing stage. The dimensionless parameter ratio of upstream water depth of stepped labyrinth side weir p/y1 has the greatest effect on the discharge coefficient Cd, accounting for 55.57 and 54.17% under single action and other parameter interactions, respectively. Dimensionless step number bs/L has little effect on Cd, which can be ignored. Meanwhile, when the number of steps is less (N = 4) and the internal head angle is smaller (θ = 45°), a larger discharge coefficient value can be obtained.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138951682","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}
I. Zahidi, Mun Ee Yau, Alex Lechner, Karen Lourdes
Social values of land use are often excluded when undertaking integrated flood management as they are harder to quantify. To fill this research gap, a geographic information system application called Social Values for Ecosystem Services was used to assess, map and quantify the perceived social values of flood-prone land use in Kuala Selangor, Malaysia. This approach was based on a non-monetary value index (VI) calculated from responses to a quantitative social survey on the public's attitude and preference towards flood management across different land uses. The study outcome is the geospatial representation of flood-prone land use with their social values, which local communities perceive as crucial for flood management. The VI was influenced by elevation and slope, with lower elevations and flatter slopes associated with higher values. Farmland is highly favoured by the local community for flood management, whereas oil palm and rubber plantations are opposed. Tourism received the highest monetary allocations from survey respondents, with the popular firefly park consistently associated with the highest social values. This practical framework contributes to integrated flood management in facilitating decision-makers to evaluate land-use trade-offs by considering their social values when prioritising flood mitigation measures or investments.
{"title":"Modelling public social values of flood-prone land use using the GIS application SolVES","authors":"I. Zahidi, Mun Ee Yau, Alex Lechner, Karen Lourdes","doi":"10.2166/hydro.2023.010","DOIUrl":"https://doi.org/10.2166/hydro.2023.010","url":null,"abstract":"\u0000 Social values of land use are often excluded when undertaking integrated flood management as they are harder to quantify. To fill this research gap, a geographic information system application called Social Values for Ecosystem Services was used to assess, map and quantify the perceived social values of flood-prone land use in Kuala Selangor, Malaysia. This approach was based on a non-monetary value index (VI) calculated from responses to a quantitative social survey on the public's attitude and preference towards flood management across different land uses. The study outcome is the geospatial representation of flood-prone land use with their social values, which local communities perceive as crucial for flood management. The VI was influenced by elevation and slope, with lower elevations and flatter slopes associated with higher values. Farmland is highly favoured by the local community for flood management, whereas oil palm and rubber plantations are opposed. Tourism received the highest monetary allocations from survey respondents, with the popular firefly park consistently associated with the highest social values. This practical framework contributes to integrated flood management in facilitating decision-makers to evaluate land-use trade-offs by considering their social values when prioritising flood mitigation measures or investments.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138968040","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}
Chien Quyet Nguyen, Tuyen Thi Tran, Trang Thanh Thi Nguyen, Thuy Ha Thi Nguyen, T. S. Astarkhanova, Luong Van Vu, Khac Tai Dau, Hieu Ngoc Nguyen, Giang Hương Pham, D. Nguyen, Indra Prakash, Binh Pham
Soil Erosion Susceptibility Mapping (SESM) is one of the practical approaches for managing and mitigating soil erosion. This study applied four Machine Learning (ML) models namely the Multilayer Perceptron (MLP) classifier, AdaBoost, Ridge classifier, and Gradient Boosting classifier to perform SESM in a region of Nghe An province, Vietnam. The development of these models incorporated seven factors influencing soil erosion: slope degree, slope aspect, curvature, elevation, Normalized Difference Vegetation Index (NDVI), rainfall, and soil type. These factors were determined based on 685 identified soil erosion locations. According to SHapley Additive exPlanations (SHAP) analysis, soil type emerged as the most significant factor influencing soil erosion. Among all the developed models, the Gradient Boosting classifier demonstrated the highest prediction power, followed by the MLP classifier, Ridge classifier, and AdaBoost, respectively. Therefore, the Gradient Boosting classifier is recommended for accurate SESM in other regions too, taking into account the local geo-environmental factors.
{"title":"Mapping of soil erosion susceptibility using advanced machine learning models at Nghe An, Vietnam","authors":"Chien Quyet Nguyen, Tuyen Thi Tran, Trang Thanh Thi Nguyen, Thuy Ha Thi Nguyen, T. S. Astarkhanova, Luong Van Vu, Khac Tai Dau, Hieu Ngoc Nguyen, Giang Hương Pham, D. Nguyen, Indra Prakash, Binh Pham","doi":"10.2166/hydro.2023.327","DOIUrl":"https://doi.org/10.2166/hydro.2023.327","url":null,"abstract":"\u0000 Soil Erosion Susceptibility Mapping (SESM) is one of the practical approaches for managing and mitigating soil erosion. This study applied four Machine Learning (ML) models namely the Multilayer Perceptron (MLP) classifier, AdaBoost, Ridge classifier, and Gradient Boosting classifier to perform SESM in a region of Nghe An province, Vietnam. The development of these models incorporated seven factors influencing soil erosion: slope degree, slope aspect, curvature, elevation, Normalized Difference Vegetation Index (NDVI), rainfall, and soil type. These factors were determined based on 685 identified soil erosion locations. According to SHapley Additive exPlanations (SHAP) analysis, soil type emerged as the most significant factor influencing soil erosion. Among all the developed models, the Gradient Boosting classifier demonstrated the highest prediction power, followed by the MLP classifier, Ridge classifier, and AdaBoost, respectively. Therefore, the Gradient Boosting classifier is recommended for accurate SESM in other regions too, taking into account the local geo-environmental factors.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139000272","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}
Lyce Ndolo Umba, Ilham Yahya Amir, Gebre Gelete, Hüseyin Gökçekuş, Ikenna D. Uwanuakwa
Rainfall-runoff modelling is a critical component of hydrological studies, and its accuracy is essential for water resource management. Recent advances in machine learning have led to the development of more sophisticated rainfall-runoff models, but there is still room for improvement. This study proposes a novel approach to streamflow modelling that uses the artificial hummingbird algorithm (AHA) to optimize the boosted tree algorithm. the AHA-boosted tree algorithm model was compared against two established methods, the support vector machine (SVM) and the Gaussian process regression (GPR), using a variety of statistical and graphical performance measures. The results showed that the AHA-boosted tree algorithm model significantly outperformed the SVM and GPR models, with an R2 of 0.932, RMSE of 5.358 m3/s, MAE of 2.365 m3/s, and MSE of 28.705 m3/s. The SVM model followed while the GPR model had the least accurate performance. However, all models underperformed in capturing the peak flow of the hydrograph. Evaluations using both statistical and graphical performance measures, including time series plots, scatter plots, and Taylor diagrams, were critical in this assessment. The results suggest that the AHA-boosted tree algorithm could potentially be a superior alternative for enhancing the precision of rainfall-runoff modelling, despite certain challenges in predicting peak flow events.
{"title":"Artificial hummingbird algorithm-optimized boosted tree for improved rainfall-runoff modelling","authors":"Lyce Ndolo Umba, Ilham Yahya Amir, Gebre Gelete, Hüseyin Gökçekuş, Ikenna D. Uwanuakwa","doi":"10.2166/hydro.2023.187","DOIUrl":"https://doi.org/10.2166/hydro.2023.187","url":null,"abstract":"\u0000 Rainfall-runoff modelling is a critical component of hydrological studies, and its accuracy is essential for water resource management. Recent advances in machine learning have led to the development of more sophisticated rainfall-runoff models, but there is still room for improvement. This study proposes a novel approach to streamflow modelling that uses the artificial hummingbird algorithm (AHA) to optimize the boosted tree algorithm. the AHA-boosted tree algorithm model was compared against two established methods, the support vector machine (SVM) and the Gaussian process regression (GPR), using a variety of statistical and graphical performance measures. The results showed that the AHA-boosted tree algorithm model significantly outperformed the SVM and GPR models, with an R2 of 0.932, RMSE of 5.358 m3/s, MAE of 2.365 m3/s, and MSE of 28.705 m3/s. The SVM model followed while the GPR model had the least accurate performance. However, all models underperformed in capturing the peak flow of the hydrograph. Evaluations using both statistical and graphical performance measures, including time series plots, scatter plots, and Taylor diagrams, were critical in this assessment. The results suggest that the AHA-boosted tree algorithm could potentially be a superior alternative for enhancing the precision of rainfall-runoff modelling, despite certain challenges in predicting peak flow events.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139006755","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}
Pranit Dongare, Kul Vaibhav Sharma, Vijendra Kumar, Aneesh Mathew
Urban settlement depends on water distribution networks for clean and safe drinking water. This research incorporates geographic information systems (GIS), remote sensing (RS), and hydraulic modelling software EPANET to analyze and construct water distribution systems in Bota town, India. Satellite images and hydrological data have been utilized for management of the Bota town's water supply network, sources to cater the demand for urban centres. EPANET simulates hydraulic behaviour in the water distribution system under different operating situations. EPANET simulation shows network leaks, low pressure, and substantial head loss. These findings have advised for water distribution system improvements by analyzing network shortcomings. Booster pumps, new pipelines, and repairing of existing leakages are examples of such improvements. GIS, remote sensing, and EPANET provided a comprehensive water distribution system study and more accurate and efficient improvement identification. This study emphasizes the necessity of new technologies in water distribution system analysis and design. The study solves Bota town's water distribution system problems of low pressure, high head loss, and leaks utilizing GIS, remote sensing, and EPANET. The findings of this research can help in enhancing the water delivery systems in other towns with comparable issues.
{"title":"Water distribution system modelling of GIS–remote sensing and EPANET for the integrated efficient design","authors":"Pranit Dongare, Kul Vaibhav Sharma, Vijendra Kumar, Aneesh Mathew","doi":"10.2166/hydro.2023.281","DOIUrl":"https://doi.org/10.2166/hydro.2023.281","url":null,"abstract":"\u0000 \u0000 Urban settlement depends on water distribution networks for clean and safe drinking water. This research incorporates geographic information systems (GIS), remote sensing (RS), and hydraulic modelling software EPANET to analyze and construct water distribution systems in Bota town, India. Satellite images and hydrological data have been utilized for management of the Bota town's water supply network, sources to cater the demand for urban centres. EPANET simulates hydraulic behaviour in the water distribution system under different operating situations. EPANET simulation shows network leaks, low pressure, and substantial head loss. These findings have advised for water distribution system improvements by analyzing network shortcomings. Booster pumps, new pipelines, and repairing of existing leakages are examples of such improvements. GIS, remote sensing, and EPANET provided a comprehensive water distribution system study and more accurate and efficient improvement identification. This study emphasizes the necessity of new technologies in water distribution system analysis and design. The study solves Bota town's water distribution system problems of low pressure, high head loss, and leaks utilizing GIS, remote sensing, and EPANET. The findings of this research can help in enhancing the water delivery systems in other towns with comparable issues.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139004752","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}
Accurate runoff prediction is vital in optimizing reservoir scheduling, efficiently managing water resources, and ensuring the effective utilization of water resources. In this paper, a hybrid prediction model combining complete ensemble empirical mode decomposition with adaptive noise, variational mode decomposition, CABES, and long short-term memory network (CEEMDAN-VMD-CABES-LSTM) is proposed. Firstly, CEEMDAN is used to decompose the original data, and the high-frequency component obtained from the CEEMDAN decomposition is decomposed using VMD. Then, each component is input into the LSTM optimized by CABES for prediction. Finally, the results of individual component predictions are combined and reconstructed to produce the monthly runoff predictions. The hybrid model is employed to predict the monthly runoff at the Xiajiang hydrological station and the Yingluoxia hydrological station. A comprehensive comparison is conducted with other models including BP, LSTM, SSA-LSTM, bald eagle search (BES)-LSTM, CABES-LSTM, CEEMDAN-CABES-LSTM, and VMD-CABES-LSTM. The assessment of each model's prediction performance uses four evaluation indexes. Results reveal that the CEEMDAN-VMD-CABES-LSTM model showcased the highest forecast accuracy among all the models evaluated. Compared with the single LSTM, the root mean square error (RMSE) and mean absolute percentage error (MAPE) of the Xiajiang hydrological station decreased by 71.09 and 65.26%, respectively, and the RMSE and MAPE of the Yingluoxia hydrological station decreased by 65.13 and 40.42%, respectively. The R and Nash efficiency coefficient (NSEC) values obtained for both sites are near 1.
{"title":"Improved monthly runoff time series prediction using the CABES-LSTM mixture model based on CEEMDAN-VMD decomposition","authors":"Dong-mei Xu, An-dong Liao, Wenchuan Wang, Wei-can Tian, Hong-fei Zang","doi":"10.2166/hydro.2023.216","DOIUrl":"https://doi.org/10.2166/hydro.2023.216","url":null,"abstract":"\u0000 \u0000 Accurate runoff prediction is vital in optimizing reservoir scheduling, efficiently managing water resources, and ensuring the effective utilization of water resources. In this paper, a hybrid prediction model combining complete ensemble empirical mode decomposition with adaptive noise, variational mode decomposition, CABES, and long short-term memory network (CEEMDAN-VMD-CABES-LSTM) is proposed. Firstly, CEEMDAN is used to decompose the original data, and the high-frequency component obtained from the CEEMDAN decomposition is decomposed using VMD. Then, each component is input into the LSTM optimized by CABES for prediction. Finally, the results of individual component predictions are combined and reconstructed to produce the monthly runoff predictions. The hybrid model is employed to predict the monthly runoff at the Xiajiang hydrological station and the Yingluoxia hydrological station. A comprehensive comparison is conducted with other models including BP, LSTM, SSA-LSTM, bald eagle search (BES)-LSTM, CABES-LSTM, CEEMDAN-CABES-LSTM, and VMD-CABES-LSTM. The assessment of each model's prediction performance uses four evaluation indexes. Results reveal that the CEEMDAN-VMD-CABES-LSTM model showcased the highest forecast accuracy among all the models evaluated. Compared with the single LSTM, the root mean square error (RMSE) and mean absolute percentage error (MAPE) of the Xiajiang hydrological station decreased by 71.09 and 65.26%, respectively, and the RMSE and MAPE of the Yingluoxia hydrological station decreased by 65.13 and 40.42%, respectively. The R and Nash efficiency coefficient (NSEC) values obtained for both sites are near 1.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138979775","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}
Modeling of pressure-dependent users’ consumption is mandatory to simulate accurately the hydraulics of water distribution networks (WDNs). Several software solutions already exist for this purpose, but none of them actually permits the easy integration and test of new physical processes. In this paper, we propose a new Python simulator that implements a state-of-the-art pressure-dependent model (PDM) of users’ consumptions based on the Wagner’s pressure–outflow relationship (POR). We tested our simulator on eight large and complex WDNs, for different levels of users’ demands. The results show similar precision and efficiency as the ones obtained by the authors of the original model with their MATLAB implementation. Moreover, in case of fully satisfied users’ demands, our simulator provides same results as EPANET 2.0 in comparable computational times. Finally, our simulator is integrated into the open-source, collaborative, multi-platform, and Git versioned Python framework OOPNET (Object-Oriented Python framework for water distribution NETworks analyses); thus, it can be easily reused and/or extended by a large community of WDN modelers. All this work represents a preliminary step before the incorporation of new processes such as valves, pumps, and pressure-dependent background leakage outflows.
{"title":"A robust simulator of pressure-dependent consumption in Python","authors":"Camille Chambon, O. Piller, I. Mortazavi","doi":"10.2166/hydro.2023.218","DOIUrl":"https://doi.org/10.2166/hydro.2023.218","url":null,"abstract":"\u0000 \u0000 Modeling of pressure-dependent users’ consumption is mandatory to simulate accurately the hydraulics of water distribution networks (WDNs). Several software solutions already exist for this purpose, but none of them actually permits the easy integration and test of new physical processes. In this paper, we propose a new Python simulator that implements a state-of-the-art pressure-dependent model (PDM) of users’ consumptions based on the Wagner’s pressure–outflow relationship (POR). We tested our simulator on eight large and complex WDNs, for different levels of users’ demands. The results show similar precision and efficiency as the ones obtained by the authors of the original model with their MATLAB implementation. Moreover, in case of fully satisfied users’ demands, our simulator provides same results as EPANET 2.0 in comparable computational times. Finally, our simulator is integrated into the open-source, collaborative, multi-platform, and Git versioned Python framework OOPNET (Object-Oriented Python framework for water distribution NETworks analyses); thus, it can be easily reused and/or extended by a large community of WDN modelers. All this work represents a preliminary step before the incorporation of new processes such as valves, pumps, and pressure-dependent background leakage outflows.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":2.7,"publicationDate":"2023-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138983095","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}
Javad Hatamiafkoueieh, Salim Heddam, Saeed Khoshtinat, Solmaz Khazaei, Abdol-Baset Osmani, Ebrahim Nohani, Mohammad Kiomarzi, Ehsan Sharafi, John Tiefenbacher
Abstract In this study, the vote algorithm used to improve the performances of three machine-learning models including M5Prime (M5P), random forest (RF), and random tree (RT) is developed (i.e. V-M5P, V-RF, and V-RT). Developed models were tested for forecasting soil temperature (TS) at 1, 2, and 3 days ahead at depths of 5 and 50 cm. All models were developed using different climatic variables, including mean, minimum, and maximum air temperatures; sunshine hours; evaporation; and solar radiation, which were evaluated. Correlation coefficients of 0.95 for the V-M5P model, 0.95 for the V-RF model, and 0.91 for the V-RT model were recorded for both 1- and 2-day ahead forecasting at a depth of 5 cm. For 3-day ahead forecasting, V-RF was the superior model with Nash–Sutcliff efficiency (NSE) values of 0.85, compared V-M5P's value of 0.81 and V-RT's value of 0.81. The results at a depth of 5 cm indicate that V-RT was the least effective model. At a depth of 50 cm, forecasted TsS was in good agreement with measurements, and the V-RF was slightly superior. Among the limitations of the current work is that the models were unable to improve their performances by increasing the forecasting horizon.
{"title":"Enhanced forecasting of multi-step ahead daily soil temperature using advanced hybrid vote algorithm-based tree models","authors":"Javad Hatamiafkoueieh, Salim Heddam, Saeed Khoshtinat, Solmaz Khazaei, Abdol-Baset Osmani, Ebrahim Nohani, Mohammad Kiomarzi, Ehsan Sharafi, John Tiefenbacher","doi":"10.2166/hydro.2023.188","DOIUrl":"https://doi.org/10.2166/hydro.2023.188","url":null,"abstract":"Abstract In this study, the vote algorithm used to improve the performances of three machine-learning models including M5Prime (M5P), random forest (RF), and random tree (RT) is developed (i.e. V-M5P, V-RF, and V-RT). Developed models were tested for forecasting soil temperature (TS) at 1, 2, and 3 days ahead at depths of 5 and 50 cm. All models were developed using different climatic variables, including mean, minimum, and maximum air temperatures; sunshine hours; evaporation; and solar radiation, which were evaluated. Correlation coefficients of 0.95 for the V-M5P model, 0.95 for the V-RF model, and 0.91 for the V-RT model were recorded for both 1- and 2-day ahead forecasting at a depth of 5 cm. For 3-day ahead forecasting, V-RF was the superior model with Nash–Sutcliff efficiency (NSE) values of 0.85, compared V-M5P's value of 0.81 and V-RT's value of 0.81. The results at a depth of 5 cm indicate that V-RT was the least effective model. At a depth of 50 cm, forecasted TsS was in good agreement with measurements, and the V-RF was slightly superior. Among the limitations of the current work is that the models were unable to improve their performances by increasing the forecasting horizon.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135041788","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 The accurate prediction of maximum erosion depth in riverbeds is crucial for early protection of bank slopes. In this study, K-means clustering analysis was used for outlier identification and feature selection, resulting in Plan 1 with six influential features. Plan 2 included features selected by existing methods. Regression models were built using Support Vector Regression, Random Forest Regression (RF Regression), and eXtreme Gradient Boosting on sample data from Plan 1 and Plan 2. To enhance accuracy, a Stacking method with a feed-forward neural network was introduced as the meta-learner. Model performance was evaluated using root mean squared error, mean absolute error, mean absolute percentage error, and R2 coefficients. The results demonstrate that the performance of the three models in Plan 1 outperformed that of Plan 2, with improvements in R2 values of 0.0025, 0.0423, and 0.0205, respectively. Among the three regression models in Plan 1, RF Regression performs the best with an R2 value of 0.9149 but still lower than the 0.9389 achieved by the Stacking fusion model. Compared to the existing formulas, the Stacking model exhibits superior predictive performance. This study verifies the effectiveness of combining clustering analysis, feature selection, and the Stacking method in predicting maximum scour depth in bends, providing a novel approach for bank protection design.
{"title":"Prediction of maximum scour depth in river bends by the Stacking model","authors":"Junfeng Chen, Xiaoquan Zhou, Lirong Xiao, Yuhang Huang","doi":"10.2166/hydro.2023.177","DOIUrl":"https://doi.org/10.2166/hydro.2023.177","url":null,"abstract":"Abstract The accurate prediction of maximum erosion depth in riverbeds is crucial for early protection of bank slopes. In this study, K-means clustering analysis was used for outlier identification and feature selection, resulting in Plan 1 with six influential features. Plan 2 included features selected by existing methods. Regression models were built using Support Vector Regression, Random Forest Regression (RF Regression), and eXtreme Gradient Boosting on sample data from Plan 1 and Plan 2. To enhance accuracy, a Stacking method with a feed-forward neural network was introduced as the meta-learner. Model performance was evaluated using root mean squared error, mean absolute error, mean absolute percentage error, and R2 coefficients. The results demonstrate that the performance of the three models in Plan 1 outperformed that of Plan 2, with improvements in R2 values of 0.0025, 0.0423, and 0.0205, respectively. Among the three regression models in Plan 1, RF Regression performs the best with an R2 value of 0.9149 but still lower than the 0.9389 achieved by the Stacking fusion model. Compared to the existing formulas, the Stacking model exhibits superior predictive performance. This study verifies the effectiveness of combining clustering analysis, feature selection, and the Stacking method in predicting maximum scour depth in bends, providing a novel approach for bank protection design.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135136521","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}
Giang Song Le, Long Thanh Tran, Loc Huu Ho, Edward Park
Abstract Coupling models of different dimensions is one of the most important yet under-represented challenges. This paper introduces a new modeling strategy to streamline a more flexible and effective integrated one-dimensional (1D)/two-dimensional (2D) model for floodplains along lowland rivers. The 1D model, utilizing the finite volume method, solves the Saint–Venant equations, while the 2D mesh employs unstructured quadrilateral elements. The two strategies couple the 1D/2D models: direct 1D/2D connection by the law of mass conservation at supernode, and lateral 1D/2D model connection by spillways at riverbank. The coupling strategy in F28 guarantees the water balance and the conservation of momentum at the integrated 1D/2D nodes. The model was applied to the Mekong Delta to address the capacity of hydrodynamic simulations integrating various water infrastructures. Results showed that the developed model has a strong potential to be applied to other lowland rivers worldwide with complex infrastructures.
{"title":"F28: a novel coupling strategy for 1D/2D hydraulic models for flood risk assessment of the Mekong Delta","authors":"Giang Song Le, Long Thanh Tran, Loc Huu Ho, Edward Park","doi":"10.2166/hydro.2023.108","DOIUrl":"https://doi.org/10.2166/hydro.2023.108","url":null,"abstract":"Abstract Coupling models of different dimensions is one of the most important yet under-represented challenges. This paper introduces a new modeling strategy to streamline a more flexible and effective integrated one-dimensional (1D)/two-dimensional (2D) model for floodplains along lowland rivers. The 1D model, utilizing the finite volume method, solves the Saint–Venant equations, while the 2D mesh employs unstructured quadrilateral elements. The two strategies couple the 1D/2D models: direct 1D/2D connection by the law of mass conservation at supernode, and lateral 1D/2D model connection by spillways at riverbank. The coupling strategy in F28 guarantees the water balance and the conservation of momentum at the integrated 1D/2D nodes. The model was applied to the Mekong Delta to address the capacity of hydrodynamic simulations integrating various water infrastructures. Results showed that the developed model has a strong potential to be applied to other lowland rivers worldwide with complex infrastructures.","PeriodicalId":54801,"journal":{"name":"Journal of Hydroinformatics","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135291546","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：