daily pan evaporation estimation using artificial neural network-based models

accurate estimation of evaporation is important for design, planning and operation of water systems. in arid zones where water resources are scarce, the estimation of this loss becomes more interesting in the planning and management of irrigation practices. this paper investigates the ability of artificial neural networks (anns) technique to improve the accuracy of daily evaporation estimation. four different anns model comprising various combinations of daily climatic variables, that is, air temperature, daily sunshine hours, wind speed, and relative humidity are developed to evaluate degree of effect of each mentioned variables on evaporation for two stations located in central part if i.r. of iran. a comparison is made between the estimates provided by the anns model and the multiple linear regression models. various statistic measures are used to evaluate the performance of the models. based on the comparisons, it was revealed that the anns computing technique could be employed successfully in modeling of evaporation process from the available climatic data. the ann also increased dramatically the accuracy of evaporation estimation compare to the multiple linear regression models. [sh, karimi-googhari. daily pan evaporation estimation using artificial neural network-based models. international journal of agricultural science, research and technology, 2011; 1(4):159-163].