University of TehranIranian Journal of Soil and Water Research2008-479X50320190723Determination of Input Variables to Estimate Solar Radiation Using Entropy Theory and Principal Component AnalysisDetermination of Input Variables to Estimate Solar Radiation Using Entropy Theory and Principal Component Analysis6256397199210.22059/ijswr.2018.257150.667906FABabakMohammadiIrrigation &amp; Reclamation Engrg. Dept.
University of Tehran
Karaj, Iran.ZahraAghashariatmadariAssistant Prof.,
Irrigation & Reclamation Engrg. Dept.
University of Tehran
Karaj, Iran.
Tel/Fax:+98-263-22411190000-0002-9555-086XRoozbehMoazenzadehAssistant professor, Soil and Water Department, Faculty of Agriculture, Shahrood University of Technology, Shahrood, Iran0000-0002-1057-3801Journal Article20180509Solar radiation arriving to the land surface is one of the major variables that is used in projects and hydrological, agricultural, meteorological and climatic models. In this study, the functionality of the <span style="text-decoration: underline;">principal</span> component analysis (PCA) and the entropy theory (EN) for determination of inputs to multilevel perceptron artificial neural network (MLP), artificial neural network, radial basis function (RBF), support vector machine (SVM)and genetic programming (GEP), was investigated for estimation of solar radiation at two stations (Kerman and Mashhad) during 1984-2005 and 1980-2004 periods, respectively. The average temperature, mean water deficit pressure, minimum temperature, maximum temperature, sunshine, relative humidity, dew point temperature, hourly vapor pressure, horizontal visibility and water content were selected as inputs of pre-processing methods. The obtained results in <span style="text-decoration: underline;">Kerman</span> station showed that the ENT-MLP model with RMSE=38.36 (Mj /m2) and R<sup>2</sup> = 0.93 have had the best performance. Also in Mashhad station, PCA-MLP model with RMSE=79.75 (Mj / m2) and R<sup>2</sup> = 0.77 had the best performance. In general, the both pre-processing principal component analysis and entropy theory were recognized as the proper methods for determination of estimating models input to estimate solar radiation.Solar radiation arriving to the land surface is one of the major variables that is used in projects and hydrological, agricultural, meteorological and climatic models. In this study, the functionality of the <span style="text-decoration: underline;">principal</span> component analysis (PCA) and the entropy theory (EN) for determination of inputs to multilevel perceptron artificial neural network (MLP), artificial neural network, radial basis function (RBF), support vector machine (SVM)and genetic programming (GEP), was investigated for estimation of solar radiation at two stations (Kerman and Mashhad) during 1984-2005 and 1980-2004 periods, respectively. The average temperature, mean water deficit pressure, minimum temperature, maximum temperature, sunshine, relative humidity, dew point temperature, hourly vapor pressure, horizontal visibility and water content were selected as inputs of pre-processing methods. The obtained results in <span style="text-decoration: underline;">Kerman</span> station showed that the ENT-MLP model with RMSE=38.36 (Mj /m2) and R<sup>2</sup> = 0.93 have had the best performance. Also in Mashhad station, PCA-MLP model with RMSE=79.75 (Mj / m2) and R<sup>2</sup> = 0.77 had the best performance. In general, the both pre-processing principal component analysis and entropy theory were recognized as the proper methods for determination of estimating models input to estimate solar radiation.https://ijswr.ut.ac.ir/article_71992_9c270cd99439ebe0f54799f601af7fc8.pdf