A Comparison of Two Solar Radiation Models Using Artificial Neural Networks and Remote Sensing in Turkey


YILDIZ B. Y. , Sahin M., ŞENKAL O. , Pestemalci V. , EMRAHOĞLU N.

ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS, vol.35, no.3, pp.209-217, 2013 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 35 Issue: 3
  • Publication Date: 2013
  • Doi Number: 10.1080/15567036.2011.650276
  • Title of Journal : ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS
  • Page Numbers: pp.209-217

Abstract

This study introduces artificial neural networks for the estimation of solar radiation using model 1 (latitude, longitude, altitude, month, and meteorological land surface temperature) and model 2 (latitude, longitude, altitude, month, and satellite land surface temperature) data in Turkey. Price method was used for the estimation of land surface temperature values. Scale conjugate gradiant learning algorithms and logistic sigmoid transfer function were used in the network. R 2 with model 1 and model 2 values have been found to be 96.93 and 97.24% (training stations), 80.41 and 82.37% (testing stations), respectively. These results are sufficient to predict the solar radiation.