An artificial neural network ensemble model for estimating global solar radiation from Meteosat satellite images

An optimized artificial neural network ensemble model is built to estimate daily global solar radiation over large areas. The model uses clear-sky estimates and satellite images as input variables. Unlike most studies using satellite imagery based on visible channels, our model also exploits all information within infrared channels of the Meteosat 9 satellite. A genetic algorithm is used to optimize selection of model inputs, for which twelve are selected – eleven 3-km Meteosat 9 channels and one clear-sky term. The model is validated in Andalusia (Spain) from January 2008 through December 2008. Measured data from 83 stations across the region are used, 65 for training and 18 independent ones for testing the model. At the latter stations, the ensemble model yields an overall root mean square error of 6.74% and correlation coefficient of 99%; the generated estimates are relatively accurate and errors spatially uniform. The model yields reliable results even on cloudy days, improving on current models based on satellite imagery.

[1]  P. Ineichen.  Comparison of eight clear sky broadband models against 16 independent data banks , 2006 .

[2]  Francesco Falciani,et al.  GALGO: an R package for multivariate variable selection using genetic algorithms , 2006, Bioinform..

[3]  L. Wald,et al.  On the clear sky model of the ESRA — European Solar Radiation Atlas — with respect to the heliosat method , 2000 .

[4]  C. F. Ratto,et al.  Solar irradiance estimation from geostationary satellite data: II. Physical models☆ , 1993 .

[5]  L. Wald,et al.  The method Heliosat-2 for deriving shortwave solar radiation from satellite images , 2004 .

[6]  H. Akaike.  A new look at the statistical model identification , 1974 .

[7]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[8]  Gabriel López,et al.  Daily solar irradiation estimation over a mountainous area using artificial neural networks , 2008 .

[9]  David Pozo-Vázquez,et al.  A comparative study of ordinary and residual kriging techniques for mapping global solar radiation over southern Spain , 2009 .

[10]  Joseph A. Jervase,et al.  Solar radiation estimation using artificial neural networks , 2002 .

[11]  Martin T. Hagan,et al.  Neural network design , 1995 .

[12]  J. A. Ruiz-Arias,et al.  A topographic geostatistical approach for mapping monthly mean values of daily global solar radiation: A case study in southern Spain , 2011 .

[13]  Serm Janjai,et al.  Estimation of solar radiation over Cambodia from long-term satellite data , 2011 .

[14]  Soteris A. Kalogirou,et al.  Artificial neural networks in renewable energy systems applications: a review , 2001 .

[15]  P. Ineichen,et al.  Derivation of Cloud Index from Geostationary Satellites and Application to the Production of Solar Irradiance and Daylight Illuminance Data , 1999 .

[16]  P. Gavilán,et al.  Guidelines on validation procedures for meteorological data from automatic weather stations , 2011 .

[17]  Jun Qin,et al.  A simple and efficient algorithm to estimate daily global solar radiation from geostationary satellite data , 2011 .

[18]  Jesús Polo,et al.  A new statistical approach for deriving global solar radiation from satellite images , 2009 .

[19]  A. Ghanbarzadeh,et al.  The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data , 2010 .

[20]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[21]  Herman Eerens,et al.  Evaluation of MSG-derived global radiation estimates for application in a regional crop model , 2012 .

[22]  F. S. Tymvios,et al.  Comparative study of Ångström's and artificial neural networks' methodologies in estimating global solar radiation , 2005 .

[23]  Ahmet Koca,et al.  Estimation of solar radiation using artificial neural networks with different input parameters for Mediterranean region of Anatolia in Turkey , 2011, Expert Syst. Appl..

[24]  J. Tovar-Pescador,et al.  A comparative analysis of DEM‐based models to estimate the solar radiation in mountainous terrain , 2009, Int. J. Geogr. Inf. Sci..

[25]  David Pozo-Vázquez,et al.  Generation of synthetic daily global solar radiation data based on ERA-Interim reanalysis and artifi , 2011 .

[26]  Richard Perez,et al.  HIGH PERFORMANCE MSG SATELLITE MODEL FOR OPERATIONAL SOLAR ENERGY APPLICATIONS , 2010 .

[27]  Francisco J. Batlles,et al.  Determination of atmospheric parameters to estimate global radiation in areas of complex topography: Generation of global irradiation map , 2008 .

[28]  M. Iqbal.  An introduction to solar radiation , 1983 .

[29]  O. Şenkal.  Modeling of solar radiation using remote sensing and artificial neural network in Turkey , 2010 .

[30]  H. Guillard,et al.  A method for the determination of the global solar radiation from meteorological satellite data , 1986 .

[31]  Robert Frouin,et al.  A review of satellite methods to derive surface shortwave irradiance , 1995 .

[32]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[33]  Soteris A. Kalogirou,et al.  Applications of artificial neural-networks for energy systems , 2000 .

[34]  P. Ineichen,et al.  A new operational model for satellite-derived irradiances: description and validation , 2002 .

[35]  R. Perez,et al.  IMPROVING THE PERFORMANCE OF SATELLITE-TO-IRRADIANCE MODELS USING THE SATELLITE'S INFRARED SENSORS , 2010 .

[36]  R. Perez,et al.  Effective Accuracy of Satellite-Derived Hourly Irradiances , 1999 .

[37]  J. Schmetz,et al.  AN INTRODUCTION TO METEOSAT SECOND GENERATION (MSG) , 2002 .

[38]  Jesús Polo,et al.  Artificial intelligence techniques applied to hourly global irradiance estimation from satellite-derived cloud index , 2005 .

[39]  S. N. Alamri,et al.  ANN-based modelling and estimation of daily global solar radiation data: A case study , 2009 .

[40]  M. Ranjan,et al.  Solar resource estimation using artificial neural networks and comparison with other correlation models , 2003 .

[41]  Yingni Jiang,et al.  Computation of monthly mean daily global solar radiation in China using artificial neural networks and comparison with other empirical models , 2009 .

[42]  Adel Mellit,et al.  Prediction of daily global solar irradiation data using Bayesian neural network: A comparative study , 2012 .

[43]  Amanda J. C. Sharkey,et al.  Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems , 1999 .

[44]  Richard Perez,et al.  COMPARING SATELLITE REMOTE SENSING AND GROUND NETWORK MEASUREMENTS FOR THE PRODUCTION OF SITE/TIME SPECIFIC IRRADIANCE DATA , 1997 .

[45]  L. F. Zarzalejo,et al.  Solar resources estimation combining digital terrain models and satellite images techniques , 2010 .

[46]  C. F. Ratto,et al.  Solar irradiance estimation from geostationary satellite data: I. Statistical models☆ , 1993 .

[47]  Vincent Calcagno,et al.  glmulti: An R Package for Easy Automated Model Selection with (Generalized) Linear Models , 2010 .

[48]  A. Adane,et al.  Satellite approach based on cloud cover classification: Estimation of hourly global solar radiation from meteosat images , 2008 .

[49]  M. Nunez,et al.  Development of a method for generating operational solar radiation maps from satellite data for a tropical environment , 2005 .

[50]  Soteris A. Kalogirou,et al.  Artificial intelligence techniques for photovoltaic applications: A review , 2008 .

[51]  Gabriel López,et al.  Selection of input parameters to model direct solar irradiance by using artificial neural networks , 2004 .

[52]  Hamdy K. Elminir,et al.  Prediction of hourly and daily diffuse fraction using neural network, as compared to linear regression models , 2007 .

[53]  Jesús Polo,et al.  Iterative filtering of ground data for qualifying statistical models for solar irradiance estimation from satellite data , 2006 .