The Estimation of Solar Radiation for Different Time Periods

ŞENKAL O., ŞAHİN M. C., Pestemalci V.

ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS, cilt.32, sa.13, ss.1176-1184, 2010 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 32 Sayı: 13
  • Basım Tarihi: 2010
  • Doi Numarası: 10.1080/15567030902967850
  • Dergi Adı: ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.1176-1184
  • Anahtar Kelimeler: generalized regression neural network, land surface temperature, satellite data, solar radiation, Turkey, LAND-SURFACE-TEMPERATURE, ARTIFICIAL NEURAL-NETWORKS, SPLIT-WINDOW ALGORITHM, TURKEY, EMISSIVITY, SPEED
  • Çukurova Üniversitesi Adresli: Evet

Özet

In this study, the method of Becker and Li was proposed for the estimation of monthly global land surface temperature values from meteorological satellite (NOAA-AVHRR) data. This study introduces generalized regression neural network for the estimation of solar radiation. In order to train the neural network, meteorological satellite and geographical data for the period from 2002 for short term (Adana) and 1998-2002 for long term (Izmir) in Turkey was used. Meteorological satellite and geographical data (latitude, longitude, altitude, month, and mean land surface temperature) are used in the input layer of the network. Solar radiation is the output. Root mean squared and correlation coefficient data between estimated and ground values are found with artificial neural networks values. These values have been found to be 0.0144 MJm(-2) and 99.75% (short term) and 0.1381 MJm(-2) and 99.26% (long term), respectively. In recent studies, there are some effective techniques about prediction solar radiation data, which is useful to the designers of solar energy systems. Nevertheless, there is no study about the prediction of solar radiation, which has used the artificial neural networks method with land surface temperature data provided from meteorological satellite data.