Estimation of solar radiation by implementing optimized artificial neural network-genetic algorithm and utilizing the meteorological parameters

Document Type : Research Paper

Authors

1 Ph.D. Candidate of Irrigation and Drainage, Department of Water Engineering, Faculty of Agriculture, Tabriz University, Tabriz, Iran

2 Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran

3 Professor, Department of Water Engineering, Faculty of Agriculture, Tabriz University, Tabriz, Iran

Abstract

Solar radiation is one of the key factors in the fields of agriculture, hydrology and meteorology and plays an essential role in various physical, biological and chemical processes such as snowmelt, evaporation and photosynthesis of plants and crop production and accurate estimation of this parameter has great importance. Accordingly, in this study, the amounts of daily solar radiation were estimated using artificial neural network and artificial neural network-genetic algorithm in six stations of Ardabil province including Ardabil, Bilehsavar, Sareyn, Germi, Meshgin Shahr and Nir. The data used in this research include maximum, minimum and average temperature, relative humidity and wind speed of the mentioned stations in a time period of two years (2017-2018) which are used in eight different combinations as input data of the models. Also, statistical indices of correlation coefficient, root mean square error, Wilmot index, Kling-Gupta efficiency and Taylor diagrams have been used to compare the obtained results. Generally, the obtained results indicated that in the artificial neural network method, the models of Bilehsavar station and in the artificial neural network-genetic algorithm method, the models of Ardabil station recorded the most accurate results. Also, MLP-VIII model in Bilehsavar station with a correlation coefficient of 0.856, root mean square error of 0.319 (MJ/m2d), Kling-Gupta efficiency of 0.659 and Wilmot index of 0.893 have the best performance in the utilized models. As a conclusion, the use of artificial neural network-genetic algorithm method in estimating solar radiation as accurately as possible was recommended.

Keywords

Main Subjects