Modelling Monthly Potential Evapotranspiration (ETP) Using Generalized Regression Neural Networks (GRNN): Case Study of the Semi-Arid Region of Guelma Northeast of Algeria.

Abstract

The aim of this study is to estimate the monthly potential evapotranspiration (ETP) based on class pan evaporation (EP), using climatic data, in the agro meteorological conditions of the semi-arid region of Guelma, Northeast of Algeria country, using Generalized Regression Neural Networks (GRNN) based approach and multiple linear regression model (MLR). For the purpose of this paper, the generalized regression neural networks model (GRNN) and multiple linear regression models are developed and compared in order to estimate ETP. Various monthly climatic data, that is, monthly sunshine duration, maximum, minimum and mean air temperature, and wind speed from Guelma, Algeria, are used as inputs to the GRNN and MLR models. The performances of the models are evaluated using root mean square errors (RMSE), mean absolute error (MAE), Willmott index of agreement (d) and correlation coefficient (CC) statistics. Based on the comparisons, the GRNN was found to perform better than the MLR model.