Figure - uploaded by A. Hussain
Content may be subject to copyright.
Source publication
Flow through the rectangular side weir is a spatially varied type flow with decreasing discharge and
used as a flow diversion structure. They are mainly used in the field of hydraulic, irrigation, and environmental
engineering for diverting and controlling the flow of water in irrigation–drainage systems, drainage canal systems,
and wastewater c...
Contexts in source publication
Context 1
... the experiments conducted under subcritical flow conditions. The range of experimental data collected for the present study is shown in Table 1. ...Context 2
... order to verify the accuracy of the existing models, the entire available range of data was used. Table 1 shows the range of data for all the parameters used in the present investigation and Table 2 shows the models proposed by Borghei et al. (1999), Ghodsian (1997), andShariq et al. (2018). These models were selected for comparison in the present study. ...Citations
... Borghei et al. (1999); Jalili and Borghei (1996) considered the effect of L/b and p/y1 on Cd. Additionally, Agaccioglu and Yüksel (1998), Emiroglu et al. (2011), Hussain et al. (2021, and Kaya et al. (2011) found that Cd values tend to increase with increasing L/b values. Fig. 9. ...
The present study used three machine learning models, including Least Square Support Vector Regression (LSSVR) and two non-parametric models, namely, Quantile Regression Forest (QRF) and Gaussian Process Regression (GPR), to quantify uncertainty and precisely predict the side weir discharge coefficient (Cd) in rectangular channels. So, 15 input structures were examined to develop the models. The results revealed that the machine learning models used in the study offered better accuracy compared to the classical equations. While the LSSVR and QRF models provided a good prediction performance, the GPR slightly outperformed them. The best input structure that was developed included all four dimensionless parameters. Sensitivity analysis was conducted to identify the effective parameters. To evaluate the uncertainty in the predictions, the LSSVR, QRF, and GPR were used to generate prediction intervals (PI), which quantify the uncertainty coupled with point prediction. Among the implemented models, the GPR and LSSVR models provided more reliable results based on PI width and the percentage of observed data covered by PI. According to point prediction and uncertainty analysis, it was concluded that the GPR model had a lower uncertainty and could be successfully used to predict Cd.
... The past researchers proposed models for the estimation of discharge coefficient of weirs using Gene Expression Programming (GEP) (Ebtehaj et al. 2015a;Azimi et al. 2017a;Hussain et al. 2021). Hybrid neuro-fuzzy models have also been employed to predict the discharge coefficient of weirs and side orifices using hybrid neuro-fuzzy models (Khoshbin et al. 2016;Azimi et al. 2017b;Ebtehaj et al. 2015b) used the Group Method of Data Handling (GMDH) to predict the discharge coefficient of orifices with square sides, while Akhbari et al. (2017) determined the discharge coefficient of triangular weirs using radial basis function neural networks. ...
A side orifice is a mechanism integrated into one or both side walls of a canal to redirect or release water from the main channel, and it has numerous applications in environmental engineering and irrigation. This research paper evaluates different artificial neural network (ANN) modeling algorithms for the estimation of discharge of a circular side orifice in open channels under free flow conditions. Four training algorithm were compared, namely, Gradient Descent (ANN-GD), Levenberg–Marquardt (ANN-LM), Gradient-Descent with Momentum (GDM), and Gradient-Descent with Adaptive Learning (GDA). Among all the models developed for discharge prediction through a circular side orifice, the ANN-LM model, which employed the LM algorithm for optimization during the backpropagation process, had the best performance during both training and testing. The AARE, R, E, and RMSE values were 3.13, 0.9994, 0.9987, and 0.0005, respectively, during training and 4.43, 0.9976, 0.9952, and 0.0010, respectively, during testing. The predicted discharge from the ANN-LM model was compared to the discharge equation proposed in the literature, and the comparison revealed that the ANN-LM model reduced the error in predicted discharge by 50%.
... (6) using the remaining 20% of the data collected in the present study. Generally, 70-80% of the total data are used for developing an equation and 20-30% of the total data for its validation [2,7,8,23]. Fig. 8 shows the comparison between the predicted and observed values of C d for the training and validation data sets. ...
... The absolute percentage error in discharge is calculated using Eqs. (6), (7) and (11), 7 for free flow and submerged flow, respectively. It is apparent from Fig. 16 that 90% of data lies within the 10% error of discharge calculated using both approaches for free flow and submerged flow conditions. ...
... (7) for submerged flow conditions were plotted inFig. 14with their corresponding observed values. ...
A gabion weir is considered more environmentally friendly than a solid weir, as its porosity allows aquatic life and physical matter to move through it. In the present study, a series of laboratory experiments were conducted on flow over gabion weir and solid weir under free flow and submerged flow conditions. The collected data have been used to develop equations for the coefficient of discharge of gabion weir and solid weir. Two approaches are developed for the estimation of discharge over the gabion weir. Approach-I shows better results for the estimation of the discharge over gabion weir under free-flow and submerged flow conditions. Further, water surface profiles over the solid weir and gabion weirs with different porosities are observed during experimentation. It is also observed that the ratio of head over the gabion weir to crest height is an effective parameter for the coefficient of discharge of gabion weir.
A rectangular basket assembled from a hexagonal mesh of heavily galvanised steel wire, filled with rock stacked atop one another to form a weir structure, is known as a Gabion weir. They are porous structures that can sometimes be vegetated and are considered an aesthetic structural solution with minimal habitat. Recently, the stepped gabion weirs have become a popular structure replacing stepped spillways that can check floods. The performance of an artificial neural network, one of the robust machine learning techniques, is investigated in predicting the inverse relative energy dissipation of the stepped gabion weir. The proposed ANN model in the present study is then compared with different machine learning techniques available in the literature. Based on performance parameters, it is observed that the proposed ANN model has the highest accuracy compared to the GMDH and GEP models in predicting the relative energy dissipation of the stepped gabion weir.KeywordsInverse relative energy dissipation (IRED)Artificial neural networkStepped gabion weirGabion number
Flooding is a widespread, recurring, and devastating natural hazard that occurs all over the world. Estimating stream flow has a significant financial impact because it can aid in water resource management and provide protection from water scarcity and potential flood damage. The objective of the study is to carry out a flood frequency analysis of the lower Tapi River Basin, Surat, and to assess which method is more suitable for finding the return period of particular peak discharge. The lower Tapi River Basin is subjected to severe floods during monsoon times. Gumbel's distribution method, Log Pearson Type III (LP3), and Generalized Extreme value probability distribution methods were employed for simulating the future flood discharge scenarios using annual peak flow data (1980–2020), i.e., 41 years from one gauging station (Nehru Bridge) of the lower Tapi River Basin. As a result, a frequency analysis was carried out to correlate the magnitude of occurrences with their frequency of occurrence using a probability distribution. The estimated design floods for different return periods (Tr), such as 2, 10, 25, 50, 100, 150, and 200, were obtained and compared. At a 5% significance level, three goodness of fit tests were used to the fitted distributions: Chi-squared, Kolmogorov–Smirnov, and Anderson–Darling. Based on the above study, it is concluded that Gumbel’s Distribution method is more reliable for the lower Tapi Basin compared to the other two methods. Hydrologists, water resources engineers, and floodplain managers will all may benefit from the study's conclusions.KeywordsFlood frequency analysisGumbel’s distribution methodLog Pearson Type-III distribution methodPeak discharge
A two-dimensional (2D) hydrodynamic (HD) model is developed for densely populated Surat city, India, located on the bank of the lower Tapi River. Surat city has experienced flooding in the past during the monsoon period due to heavy releases from the Ukai Dam situated 100 km upstream of the city. In the current study, the 2D HD model is developed for the lower Tapi basin (LTB), focusing on Surat city for the past flood that occurred in August 2006. The hourly discharge from the Ukai Dam and tidal levels at the Arabian Sea was used as upstream and downstream boundary conditions, respectively. The distributed floodplain roughness coefficient based on the existing land use land cover (LULC) of the study area is considered across the flood plain. The performance of the model is evaluated against observed water levels along the channel, including maximum flood depth across the flood plain of Surat city and found satisfactory. The developed model will be useful for the local administration in predicting maximum water depth, velocity, and flood duration for various return periods floods of high magnitude and help prioritize the mitigation strategies.Keywords2D HD modelSurat cityLower Tapi RiverUkai DamArabian Sea
Artificial intelligence (AI) and machine learning (ML) technology are bringing new opportunities in water resources engineering. ML, a subset of AI, is a significant research area of interest contributing smartly to the planning and execution of water resources projects. Still, ML in water resources engineering can explore new applications such as automatic scour detection, flood prediction and mitigation, etc. The challenges faced by the researchers in applying ML are mainly due to the acquisition of quality data and the cost involved in computational resources. This chapter reviews the history of the development of AI and ML algorithm applied in water resources. This chapter also presents the scientometric review of shallow ML algorithms, viz., linear regression, logistic regression, artificial neural network, decision trees, gene expression programming, genetic programming, multigene genetic programming, support vector machines, k-nearest neighbor, k-means clustering algorithm, AdaBoost, random forest, hidden Markov model, spectral clustering, and group method of data handling. This chapter analyzes the articles related to the shallow learning algorithms mentioned above from 1989 to 2022 and their applications in various aspects of water resource engineering.
The surface runoff can be predicted using hydrographs, and hence, the hydrographs become a prerequisite in designing hydrologic structures. The concept of unit hydrograph have been used widely in the field of hydrology in the past. There are different methods for the derivation of unit hydrographs like the ordinate method, matrix method, and the method of linear programming. In this study, a Genetic Algorithm-based optimization model has been created to identify the ordinates of unit hydrograph [U] to obtain a unique solution and avoid the challenges connected with the inversion of [P]T[P] matrix. The excess rainfall and direct runoff data sets are used to create an objective function for this purpose. The sum of the squares of the difference between the observed and the simulated direct runoffs is used to get the objective function. The simulated direct runoff values can be computed using the convolution equation [P][U] = [Q]. The Genetic Algorithm is then used to minimize the objective function in order to discover the ordinates of the unit hydrograph while taking into account, respectively, the 80%, 10%, and 10% of the total population size for elitism, crossover, and mutation. The root-mean-squared error of predicted values for three datasets obtained from the literature has been computed as 0.0126, 5.108, and 5.292.
