Development and evaluation of neural network models to estimate daily solar radiation at Córdoba, Argentina

Abstract

-The objective of this work was to develop neural network models of backpropagation type to estimate solar radiation based on extraterrestrial radiation data, daily temperature range, precipitation, cloudiness and relative sunshine duration. Data from Córdoba, Argentina, were used for development and validation. The behaviour and adjustment between values observed and estimates obtained by neural networks for different combinations of input were assessed. These estimations showed root mean square error between 3.15 and 3.88 MJ m -2 d -1 . The latter corresponds to the model that calculates radiation using only precipitation and daily temperature range. In all models, results show good adjustment to seasonal solar radiation. These results allow inferring the adequate performance and pertinence of this methodology to estimate complex phenomena, such as solar radiation.Index terms: modelling, prediction, backpropagation neural networks. Desenvolvimento e avaliação de modelos de redes neurais para estimação da irradiação solar diária em Córdoba, ArgentinaResumo -O objetivo deste trabalho foi desenvolver modelos de redes neuronais, do tipo retropropagação, para a estimação da irradiação solar, a partir de dados de irradiação solar extraterrestre, amplitude térmica, precipitação, nebulosidade e razão de insolação. O treinamento e a validação foram realizados com dados correspondentes a Córdoba, Argentina. O comportamento e ajuste entre os valores observados e os estimados pelas redes foram avaliados para diferentes combinações das variáveis de entrada, que apresentaram valores do erro quadrático médio entre 3,15 e 3,88 MJ m -2 d -1 . Este último valor corresponde ao modelo que calcula a irradiação somente utilizando precipitação e amplitude térmica diária. Os resultados exibem em todos os modelos um ajuste apropriado ao comportamento sazonal da irradiação solar e permitem concluir a pertinência e o adequado desempenho desse método para estimar fenômenos complexos como a irradiação solar.Termos para indexação: modelagem, predição, redes neurais de retropropagação.

Estimating soybean ground cover from satellite images using neural-networks models

“…For each model, in this phase, 69 patterns of data were used for MODIS and 66 for Landsat. The steps that demonstrate the training algorithm of the proposed networks were described in detail by Bocco et al (2006).…”

Comparison of Regression and Neural Networks Models to Estimate Solar Radiation

“…The general steps that describe the training algorithm of the proposed networks are described, according to Bocco et al (2006), as follows: Initialize the weights in the net with random values (step 1); read an input pattern Xp: (xp1, xp2, ..., xpN) and the desired output d (step 2); generate the output calculated by the net for the presented input. To do so, the values of the answers in each layer are obtained, until the output layer is reached (step 3).…”

“…These models can handle a large number of data, predict the contribution of these in the outcome and provide prompt and adequate predictions (Al-Alawi and Al-Hinai, 1998). Using neural networks, Bocco et al (2006) made models to estimate solar radiation at Córdoba (Argentina), Mohandes et al (1998) for Saudi Arabia and Fortin et al (2008) for Canada.…”

Using measured daily meteorological parameters to predict daily solar radiation

“…Compared to other soft computing methods, it has been barely applied to energy related problems [2,3,[55][56][57]. Although ANNs are used to predict the ''daily" solar radiation [41,[58][59][60][61][62], none of the existing studies have focused on GP-based analysis of daily solar radiation. Therefore, this study presents the GEP technique for predicting the daily solar radiation in Iran.…”