Author(s): Teramoto, Érico Tadao [UNESP] ; Dos Santos, Cícero Manoel ; Escobedo, João Francisco [UNESP] ; Dal Pai, Alexandre [UNESP] ; da Silva, Silvia Helena Modenese Gorla [UNESP]
Date: 2020
Persistent ID: http://hdl.handle.net/11449/200413
Origin: Oasisbr
Subject(s): Input variables selection; Machine learning; Solar radiation; Input variables selection; Input variables selection; Machine learning; Machine learning; Solar radiation; Solar radiation
Made available in DSpace on 2020-12-12T02:05:55Z (GMT). No. of bitstreams: 0 Previous issue date: 2020-01-01. Added 1 bitstream(s) on 2021-07-15T15:07:27Z : No. of bitstreams: 1 S0102-77862020000100035.pdf: 702039 bytes, checksum: f99133c6e2c8a76e5e5a0d94757c484d (MD5)
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)
Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)
National Aeronautics and Space Administration
In the present paper, the comparison of three of the main estimation methods of solar radiation was performed: empirical models, Artificial Neural Network (ANN) and Support Vector Machine (SVM). Four classical empirical models were calibrated and validated in order to estimate hourly solar UV data in Botucatu, São Paulo State, Brazil. Taken the empirical models as reference of accuracy and set for input variables, the performance of ANN and SVM were assessed. Through the statistical parameters Mean Bias Error (MBE) and Mean Absolute Error (MAE) was confirmed the super-iority of the SVM over the ANN and empirical models. The SVM is capable to generate better results than ANN using a less number of input variables. Among all estimation methods, SVM using the set of input variables {UV0, KT } is con-sidered the best alternative due to the smaller number of input variables and relative precision.
Campus Experimental da Unesp em Registro Universidade Estadual Paulista “Júlio de Mesquita Filho”
Campus Universitário de Altamira Universidade Federal do Pará
Faculdade de Ciências Agrárias de Botucatu Universidade Estadual Paulista “Júlio de Mesquita Filho”
Campus Experimental da Unesp em Registro Universidade Estadual Paulista “Júlio de Mesquita Filho”
Faculdade de Ciências Agrárias de Botucatu Universidade Estadual Paulista “Júlio de Mesquita Filho”
