Four variables (total cloud cover, skin temperature, total column water vapour and total column ozone) from meteorological reanalysis were used to generate synthetic daily global solar radiation via artificial neural network (ANN) techniques. The goal of our study was to predict solar radiation values in locations without ground measurements, by using the reanalysis data as an alternative to the use of satellite imagery. The model was validated in Andalusia (Spain), using measured data for nine years from 83 ground stations spread over the region. The geographical location (latitude, longitude), the day of the year, the daily clear sky global radiation, and the four meteorological variables were used as input data, while the daily global solar radiation was the only output of the ANN. Sixty five ground stations were used as training dataset and eighteen stations as independent dataset. The optimum network architecture yielded a root mean square error of 16.4\% and a correlation coefficient of 94\% for the testing stations. Furthermore, we have successfully tested the forecasting capability of the model with measured radiation values at a later time. These results demonstrate the generalization capability of this approach over unseen data and its ability to produce accurate estimates and forecasts.
%0 Journal Article
%1 LinaresRodriguez2011Generation
%A Linares-Rodr\'ıguez, Alvaro
%A Ruiz-Arias, José A.
%A Pozo-Vázquez, David
%A Tovar-Pescador, Joaqu\'ın
%D 2011
%J Energy
%K syntheticdata energy statistics solar renewables
%N 8
%P 5356--5365
%R 10.1016/j.energy.2011.06.044
%T Generation of synthetic daily global solar radiation data based on ERA-Interim reanalysis and artificial neural networks
%U http://matras.ujaen.es/pdf/2011_linaresrodriguez_ene.pdf
%V 36
%X Four variables (total cloud cover, skin temperature, total column water vapour and total column ozone) from meteorological reanalysis were used to generate synthetic daily global solar radiation via artificial neural network (ANN) techniques. The goal of our study was to predict solar radiation values in locations without ground measurements, by using the reanalysis data as an alternative to the use of satellite imagery. The model was validated in Andalusia (Spain), using measured data for nine years from 83 ground stations spread over the region. The geographical location (latitude, longitude), the day of the year, the daily clear sky global radiation, and the four meteorological variables were used as input data, while the daily global solar radiation was the only output of the ANN. Sixty five ground stations were used as training dataset and eighteen stations as independent dataset. The optimum network architecture yielded a root mean square error of 16.4\% and a correlation coefficient of 94\% for the testing stations. Furthermore, we have successfully tested the forecasting capability of the model with measured radiation values at a later time. These results demonstrate the generalization capability of this approach over unseen data and its ability to produce accurate estimates and forecasts.
@article{LinaresRodriguez2011Generation,
abstract = {Four variables (total cloud cover, skin temperature, total column water vapour and total column ozone) from meteorological reanalysis were used to generate synthetic daily global solar radiation via artificial neural network (ANN) techniques. The goal of our study was to predict solar radiation values in locations without ground measurements, by using the reanalysis data as an alternative to the use of satellite imagery. The model was validated in Andalusia (Spain), using measured data for nine years from 83 ground stations spread over the region. The geographical location (latitude, longitude), the day of the year, the daily clear sky global radiation, and the four meteorological variables were used as input data, while the daily global solar radiation was the only output of the ANN. Sixty five ground stations were used as training dataset and eighteen stations as independent dataset. The optimum network architecture yielded a root mean square error of 16.4\% and a correlation coefficient of 94\% for the testing stations. Furthermore, we have successfully tested the forecasting capability of the model with measured radiation values at a later time. These results demonstrate the generalization capability of this approach over unseen data and its ability to produce accurate estimates and forecasts.},
added-at = {2018-06-18T21:23:34.000+0200},
author = {Linares-Rodr\'{\i}guez, Alvaro and Ruiz-Arias, Jos\'{e} A. and Pozo-V\'{a}zquez, David and Tovar-Pescador, Joaqu\'{\i}n},
biburl = {https://www.bibsonomy.org/bibtex/2453f6c2c03d81e6f85adf42f28a6e49b/pbett},
citeulike-article-id = {9630728},
citeulike-attachment-1 = {2011_linaresrodriguez_ene.pdf; /pdf/user/pbett/article/9630728/891043/2011_linaresrodriguez_ene.pdf; fdcff5254db1c453ec6e1d702ef831dba80453c8},
citeulike-linkout-0 = {http://matras.ujaen.es/pdf/2011_linaresrodriguez_ene.pdf},
citeulike-linkout-1 = {http://dx.doi.org/10.1016/j.energy.2011.06.044},
comment = {(private-note)Available from http://matras.ujaen.es/en/publicaciones.php},
doi = {10.1016/j.energy.2011.06.044},
file = {2011_linaresrodriguez_ene.pdf},
interhash = {6e4281c6002b96870a59fb1bc03bbcff},
intrahash = {453f6c2c03d81e6f85adf42f28a6e49b},
issn = {03605442},
journal = {Energy},
keywords = {syntheticdata energy statistics solar renewables},
month = aug,
number = 8,
pages = {5356--5365},
posted-at = {2013-04-24 09:49:33},
priority = {2},
timestamp = {2018-06-22T18:33:17.000+0200},
title = {Generation of synthetic daily global solar radiation data based on ERA-Interim reanalysis and artificial neural networks},
url = {http://matras.ujaen.es/pdf/2011_linaresrodriguez_ene.pdf},
volume = 36,
year = 2011
}