Prediction of Horizontal Daily Global Solar irradiation using artificial neural networks (ANNs) in the Castile and Leon Region, Spain
Diez, F.J., Navas-Gracia, L.M., Chico-Santamarta, L., Correa-Guimaraes, A. and Martínez-Rodríguez, A, (2020) Prediction of Horizontal Daily Global Solar irradiation using artificial neural networks (ANNs) in the Castile and Leon Region, Spain. In: Prime Archives in Agronomy. Videleaf, Hyderabad.
|
Text
Letiticia ANNs-for-the-Daily-Prediction.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview |
Abstract
The next day's global horizontal solar irradiation is predicted using artificial neural networks (ANNs) for its application in agricultural science and technology. The time series of eight−years data is measured in an agrometeorological station, which belongs to the SIAR irrigation system (Agroclimatic Information System for Irrigation, in Spanish), located in Mansilla Mayor (León, Castile and León region, Spain). The zone has a Csb climate classification (i.e., Mediterranean Warm Summer Climate), according to Koppen−Geiger. The data for the years (2004−2010) are used for ANNs training and the 2011 as the validation year. ANN models were designed and evaluated with different numbers of inputs and neurons in the hidden layer. A neuron was used in the output layer, for all models, where the simulation of global solar irradiation for the next day on the horizontal surface results. Evaluated values of the input data were the horizontal daily global irradiation of the current day [H(t)] and two days before [H(t−1), H(t−2)], the day of the year [J(t)], and the daily clearness index [Kt(t)]. Validated results showed that best adjustment models are the ANN 7 model (RMSE = 3.76 MJ/(m2 ·d), with two inputs [H(t), Kt(t)] and four neurons in the hidden layer) and the ANN 4 model (RMSE = 3.75 MJ/(m2 ·d), with two inputs [H(t), J(t)] and two neurons in the hidden layer). Thus, the studied ANN models had better results compared to classic methods (CENSOLAR typical year, weighted moving mean, linear regression, Fourier and Markov analysis) and are practically easier as they need less input variables
| Item Type: | Book Section |
|---|---|
| Keywords: | Horizontal Daily Global Solar Irradiation, Evapotranspiration, Agrometeorology, Artificial Neuronal Networks, Computing Intelligence, Prediction |
| Divisions: | Academic Support Services |
| Depositing User: | Ms Kath Osborn |
| Date Deposited: | 10 Feb 2021 15:41 |
| Last Modified: | 10 Feb 2021 15:41 |
| URI: | https://hau.repository.guildhe.ac.uk/id/eprint/17636 |
Actions (login required)
 |
Edit Item |