Comparison of Incoming Solar Radiation at Different Air Density Regimes Using Neural Network Models

Senkal O.

RUSSIAN METEOROLOGY AND HYDROLOGY, cilt.43, sa.1, ss.49-55, 2018 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 43 Sayı: 1
  • Basım Tarihi: 2018
  • Doi Numarası: 10.3103/s1068373918010077
  • Dergi Adı: RUSSIAN METEOROLOGY AND HYDROLOGY
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.49-55
  • Çukurova Üniversitesi Adresli: Evet

Özet

This study creates a database on incoming solar radiation using artificial neural networks (ANN) and information on altitude, air temperature and pressure, water vapor pressure, dry air density, water vapor density, and mixing ratio obtained at five weather stations in Turkey. The coefficients of correlation of the calculation results for three regimes of air density with observational data for the training sample (2000-2001) are 99.24%, 99.82%, and 96.67%; for the testing sample (2002), 95.97%, 82.32%, and 95.11%. These values indicate that the usage of artificial neural networks and data of at-mosphere parameters is a correct and effective method for estimation of solar radiation and creation solar databases.