Modeling of daily pan evaporation of Lake Eǧirdir using data-driven techniques

TERZİ Ö.

2011 International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2011, Istanbul-Kadikoy, Türkiye, 15 - 18 Haziran 2011, ss.320-324, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/inista.2011.5946109
  • Basıldığı Şehir: Istanbul-Kadikoy
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.320-324
  • Anahtar Kelimeler: daily pan evaporation, gene expression programming, Lake Eǧirdir, radial basis function
  • Isparta Uygulamalı Bilimler Üniversitesi Adresli: Hayır

Özet

Gene Expression Programming (GEP) and Radial Basis Function Network (RBFN) models are developed to estimate daily pan evaporation which is an important parameter in hydrological and meteorological studies. Meteorological parameters used to estimate daily pan evaporation from Lake Eǧirdir at the southwestern part of Turkey are air temperature (Ta), water temperature (Tw), solar radiation (RC) and relative humidity (Rh). The GEP and RBFN models are developed by using different input combinations with these four parameters. The GEP model with Ta, Tw, RC and Rh parameters has the highest R2 (0.812) and the lowest MSE (0.0066 mm/day) values for testing set. The R2 value of the best RBFN model is obtained as 0.794 with Ta Tw and Rh. It can be seen that the GEP model was slightly more superior to the RBFN model. It is concluded from the results that GEP and RBFN can be proposed as an alternative to daily pan evaporation measurement. © 2011 IEEE.