Comparison of Regression and Neural Networks Models to Estimate Solar Radiation

Abstract

The incident solar radiation on soil is an important variable used in agricultural applications; it is also relevant in hydrology, meteorology and soil physics, among others. To estimate this variable, empirical models have been developed using several parameters and, recently, prognostic and prediction models based on artificial intelligence techniques such as neural networks. The aim of this work was to develop linear models and neural networks, multilayer perceptron, to estimate daily global solar radiation and compare their efficiency in its application to a region of the Province of Salta, Argentina. Relative sunshine duration, maximum and minimum temperature, rainfall, binary rainfall and extraterrestrial solar radiation data for the period 1996-2002, were used. All data were supplied by Experimental Station Salta, Instituto Nacional de Tecnología Agropecuaria (INTA), Argentina. For both, neural networks models and linear regressions, three alternative combinations of meteorological parameters were considered. Good results with both prediction methods were obtained, with root mean square error (RMSE) values between 1.99 and 1.66 MJ m -2 d -1 for linear regressions and neural networks, and coefficients of correlation (r 2 ) between 0.88 and 0.92, respectively. Even though neural networks and linear regression models can be used to predict the daily global solar radiation appropriately, neural networks produced better estimates.

Using artificial neural network in determining postharvest LIFE of kiwifruit

“…Pedotransfer functions (PF) are undirected methods that estimate time‐consuming parameters in agriculture from easily and readily measured factors. The use of prediction models such as ANNs, fuzzy inference systems and adaptive neuro‐fuzzy inference systems have been developed to obtain the PF . Nowadays, ANN is used to predict some characteristics in terms of easily and readily measured factors.…”

“…The use of prediction models such as ANNs, fuzzy inference systems and adaptive neuro-fuzzy inference systems have been developed to obtain the PF. [20][21][22] Nowadays, ANN is used to predict some characteristics in terms of easily and readily measured factors. In general, it comprises a computation system that simulates some properties of biological neurons.…”

Application of artificial neural networks to frost detection in central Chile using the next day minimum air temperature forecast

“…They can handle large amounts of data that are able to tolerate incomplete information with noise or inaccurate data, and through their learning can generate a fast and accurate prediction system. It is important to note that data required for ANN input should not necessarily respond to a specific statistical distribution (Bocco et al, 2010).…”

Estimation of net surface radiation using eddy flux tower data over a tropical mangrove forest of Sundarban, West Bengal

“…It has ability to train input data using input-output relationship based on their connections in order to provide desired function. It can estimate the output for unknown datasets (Bocco et al, 2010) with existing function. Three steps are followed while developing ANN Model i) selection of input and target data to the network along with network parameters, ii) training of the network to estimate the output and iii) testing step for validating output data with input data, which are not used in developing the model.…”