Estimation of Evaporation from a Reservoir in Semi arid Environments Using Artificial Neural Network and Climate Based Models
Mostafa Ali Benzaghta *
Soil and Water Department, Faculty of Agriculture, Sirte University, Libya.
*Author to whom correspondence should be addressed.
Abstract
Estimation of evaporation from reservoirs in arid and semi-arid regions is a very crucial issue. This paper presents an application of Artificial Neural Networks (ANN) and climate based models (Penman, Priestley-Taylor and Stephens-Stewart), for the estimation of evaporation from the Algardabiya Reservoir, near Sirt, Libya. Daily meteorological data were collected for the years 2004 to 2006 and used to develop the evaporation estimation models. The measured meteorological variables included daily observations of air temperature, relative humidity, and wind speed. A statistical analysis was undertaken to verify the accuracy of the studied models. The results of the climate based and ANN models are compared with observed evaporation data from the reservoir. The comparison shows that there was better agreement between the ANN model estimations and the observed evaporation than the climate based models.
Keywords: Evaporation, artificial neural network, modeling, reservoir, Algardabiya Reservoir semi arid region