Artificial neural network for estimating monthly reference evapotransiration under arid and semi arid environments

The objective of this study is to investigate the potential of artificial neural networks (ANNs) for estimating reference monthly evapotranspiration under arid and semi-arid environments. A simple leave one out data analysis was carried out; one neural network solution on six inputs and another six network solutions on five inputs for each monitoring station were done. Comparison of the results showed that the accuracy of ANNs is decreased when relative humidity, wind speed and solar or extraterrestrial radiation are excluded as input variables. The results also showed that monthly evapotranspiration could be computed with relatively good accuracy compared with local calibrated Hargreaves equation based on air temperature using trained ANNs at another location. We conclude, based on our overall results, that temperature-based method ANNs can be used with relatively good accuracy for water resource management, irrigation scheduling and management, and environmental assessment when data are not enough using trained ANNs from another location.