Search

Reference evapotranspiration (ET0) plays a fundamental role in irrigated agriculture. The objective of this study is to simulate monthly ET0 at a meteorological station in India using a new method, an improved support vector machine (SVM) based on the cuckoo algorithm (CA), which is known as SVM-CA. Maximum temperature, minimum temperature, relative humidity, wind speed and sunshine hours were selected as inputs for the models used in the simulation. The results of the simulation using SVM-CA were compared with those from experimental models, genetic programming (GP), model tree (M5T) and the adaptive neuro-fuzzy inference system (ANFIS). The achieved results demonstrate that the proposed SVM-CA model is able to simulate ET0 more accurately than the GP, M5T and ANFIS models. Two major indicators, namely, root mean square error (RMSE) and mean absolute error (MAE), indicated that the SVM-CA outperformed the other methods with respective reductions of 5–15% and 5–17% compared with the GP model, 12–21% and 10–22% compared with the M5T model, and 7–15% and 5–18% compared with the ANFIS model, respectively. Therefore, the proposed SVM-CA model has high potential for accurate simulation of monthly ET0 values compared with the other models. [ABSTRACT FROM AUTHOR]

Abstract Obtaining successful operation rules for dam and reservoir systems is crucial for improving water management to meet the increase in agricultural, domestic and industrial activities. Several research efforts have been developed to generate optimal operation rules for dam and reservoir systems utilizing different optimization algorithms. The main purpose of an operation rule is to minimize the gap between water supply and water demand patterns. To examine the optimized model performance, the simulation of a dam and reservoir system is usually carried out for a particular period utilizing the generated operation rule. During the simulation procedure, although reservoir inflow and evaporation are stochastic variables that are required to be forecasted during simulation, they are considered deterministic variables. This study attempts to integrate a forecasting model for reservoir inflow and evaporation with the operation rules generated from optimization models during the simulation procedure. The present study employs several optimization models to generate an optimal operation rule and two different forecasting models for reservoir inflow and reservoir evaporation. The three different optimization algorithms used in this study are the genetic algorithm (GA), particle swarm optimization (PSO) algorithm and shark machine learning algorithm (SMLA). Two different forecasting models have been developed for reservoir inflow and evaporation using the radial basis function neural network (RBF-NN) and support vector regression (SVR). It is necessary to analyze the proposed simulation procedure for examining the operation rule to comprehend the analysis under different optimal operation rules and levels of accuracy for both hydrological variables. The suggested models have been applied to generate optimal operation policies and reservoir inflow and evaporation forecasts for the Timah Tasoh dam (TTD) located in Malaysia. The results show that the major findings regarding the model performance during the simulation period indicate the necessity to pay attention to evaluating the optimized model performance by considering the results of the forecasting model for both the hydrological variables of reservoir inflow and reservoir evaporation rather than the deterministic values. [ABSTRACT FROM AUTHOR]