A nonlinear modelling-based high-order response surface method for predicting monthly pan evaporations

Abstract

Accurate modelling of pan evaporation has a vital importance in the planning and management of water resources. In this paper, the response surface method (RSM) is extended for estimation of monthly pan evaporations using high-order response surface (HORS) function. A HORS function is proposed to improve the accurate predictions with various climatic data, which are solar radiation, air temperature, relative humidity and wind speed from two stations, Antalya and Mersin, in Mediterranean Region of Turkey. The HORS predictions were compared to artificial neural networks (ANNs), neuro-fuzzy (ANFIS) and fuzzy genetic (FG) methods in these stations. Finally, the pan evaporation of Mersin station was estimated using input data of Antalya station in terms of HORS, FG, ANNs, and ANFIS modelling. Comparison results indicated that HORS models performed slightly better than FG, ANN and ANFIS models. The HORS approach could be successfully and simply applied to estimate the monthly pan evaporations.