Search

Ensuring accurate estimation of evaporation is weighty for effective planning and judicious management of available water resources for agricultural practices. Thus, this work enhances the potential of support vector regression (SVR) optimized with a novel nature-inspired algorithm, namely, Slap Swarm Algorithm (SVR-SSA) against Whale Optimization Algorithm (SVR-WOA), Multi-Verse Optimizer (SVR-MVO), Spotted Hyena Optimizer (SVR-SHO), Particle Swarm Optimization (SVR-PSO), and Penman model (PM). Daily EP (pan-evaporation) was estimated in two different agro-climatic zones (ACZ) in northern India. The optimal combination of input parameters was extracted by applying the Gamma test (GT). The outcomes of the hybrid of SVR and PM models were equated with recorded daily EP observations based on goodness-of-fit measures along with graphical scrutiny. The results of the appraisal showed that the novel hybrid SVR-SSA-5 model performed superior (MAE = 0.697, 1.556, 0.858 mm/day; RMSE = 1.116, 2.114, 1.202 mm/day; IOS = 0.250, 0.350, 0.303; NSE = 0.0.861, 0.750, 0.834; PCC = 0.929, 0.868, 0.918; IOA = 0.960, 0.925, 0.956) than other models in testing phase at Hisar, Bathinda, and Ludhiana stations, respectively. In conclusion, the hybrid SVR-SSA model was identified as more suitable, robust, and reliable than the other models for daily EP estimation in two different ACZ., Validerad;2021;Nivå 2;2021-07-15 (johcin)

Several techniques have been used for estimation of peak outflow from breach when dam failure occurs. This study proposes using a generalized regression artificial neural network (GRNN) model as a new technique for peak outflow from the dam breach estimation and compare the results of GRNN with the results of the existing methods. Six models have been built using different dam and reservoir characteristics, including depth, volume of water in the reservoir at the time of failure, the dam height and the storage capacity of the reservoir. To get the best results from GRNN model, optimized for smoothing control factor values has been done and found to be ranged from 0.03 to 0.10. Also, different scenarios for dividing data were considered for model training and testing. The recommended scenario used 90% and 10% of the total data for training and testing, respectively, and this scenario shows good performance for peak outflow prediction compared to other studied scenarios. GRNN models were assessed using three statistical indices: Mean Relative Error (MRE), Root Mean Square Error (RMSE) and Nash – Sutcliffe Efficiency (NSE). The results indicate that MRE could be reduced by using GRNN models from 20% to more than 85% compared with the existing empirical methods.

In this study, the failure of cascade dams in a tropical region is simulated using mathematical models. The simulation is considering the climate change impact. Three cascade dams for hydropower generation on the Perak River were taken as case studies. The three dams are of different designs, ages and heights which make a unique complex dam system. The proposed models were categorized as dam breach parameters model, hydrological model and hydrodynamic models. The dam breach parameters model is based on generalized regression neural network, GRNN while the hydrological model and hydrodynamic models are Mike 11 (NAM sub-model), 1-D Mike 11 and 2-D Mike 21. The GRNN was used to estimate the dam breach parameters. Dam breach parameters such as breach width, breach height and breach formation time are the key variables to estimate the peak discharge during dam break. Because of the high nonlinear relationships in dam breach parameters and their variation with time, the estimation of these parameters is considered very complex. The training and testing of GRNN models were conducted using records of more than 140 failed dams around the world in order to estimate dam breach parameters. The results obtained from GRNN models for dam breach parameters were compared with the results obtained from the existing methods. The computed value of Mean Relative Error, MRE for GRNN models were found to be ranged from 0.11 to 0.17 while values of MRE for the existing methods were founded to be ranged from 0.15 to 0.33 for dam breach width estimation. For dam failure time estimation, the values of MRE were found to be ranged from 0.08 to 0.16 for GRNN model results and from 0.34 to 0.57 for the existing methods’ results. In this study, the hydrological model was developed using Mike 11 (NAM sub-model). The Mike 11 (NAM sub-model) is a lumped conceptual model which forms part of the rainfall-runoff (RR) module of the MIKE 11 river modeling system. Time series of rainfall, evaporation and s