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

 

 

 

 

 

 

HEDDAM Salim (1), LADLANI Ibtissem (2), HOUICHI Larbi (3), DJEMILI Lakhdar (4)

 (1)Maître de conférences (MCB), Faculté des Science, Département des Sciences Agronomiques, Université 20 Août 1955, SKIKDA, E-mail: Cette adresse e-mail est protégée contre les robots spammeurs. Vous devez activer le JavaScript pour la visualiser..  

(2)Doctorant(e) en Sciences,Université Badji Mokhtar Annaba, Faculté desSciences de l’Ingénieur, Département d’Hydraulique. E-mail: Cette adresse e-mail est protégée contre les robots spammeurs. Vous devez activer le JavaScript pour la visualiser.

(3)Maître de conférences (MCA). Institut d’Architecture de Génie Civil et d’Hydraulique, Université Hadj Lakhdar - Batna. E-mail: Cette adresse e-mail est protégée contre les robots spammeurs. Vous devez activer le JavaScript pour la visualiser.

(4)Maître de conférences (MCA), Université Badji Mokhtar Annaba, Faculté desSciences de l’Ingénieur, Département d’Hydraulique. E-mail: Cette adresse e-mail est protégée contre les robots spammeurs. Vous devez activer le JavaScript pour la visualiser.

 

 

 

AbstractThe 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.

 

Key-Words— Potential Evapotranspiration (ETP), Modelling, Artificial Neural Network, GRNN, MLR

 

I.     INTRODUCTION

 

Evapotranspiration (ET) is the simultaneous process of transfer of water to the atmosphere by transpiration and evaporation in a soil–plant system [1].Accurate estimation of evapotranspiration is required for efficient irrigation management. Evapotranspiration is a complex process because it depends on several weather factors, such as temperature, radiation, humidity, wind speed and type and growth stage of the crop. Evapotranspiration (ET) being the major component of hydrological cycle will affect crop water requirement and future planning and management of water resources [2]. Evaporation pans (class A pan, US Weather Bureau) are used extensively throughout the world to estimate ETP. Evaporation pan (Ep) provides a measurement of the combined effect of temperature, humidity, wind speed and solar radiation on the reference crop evapotranspiration. This measurement can successfully be used to estimate ETP with a reasonable accuracy [3]. In this study, the potential of the generalized regression neural network (GRNN) is investigated for modeling monthly ETP based on class pan evaporation(Ep) using climatic data, in Guelma northeast of Algeria and to assess its performance relative to multiple linear regression (MLR).

 

 

Télécharger l'article