ESTIMATING OF EVAPOTRANSPIRATION USING ARTIFICIAL NEURAL NETWORK | ||
| Misr Journal of Agricultural Engineering | ||
| Article 5, Volume 37, Issue 1, January 2020, Pages 81-94 PDF (911.67 K) | ||
| Document Type: Original Article | ||
| DOI: 10.21608/mjae.2020.94971 | ||
| Author | ||
| M. A. Genaidy | ||
| Agric. Eng. Dept., Fac. of Agric., Ain Shams Univ., Egypt. | ||
| Abstract | ||
| This study investigates the application of artificial neural networks (ANNs) on the prediction of daily grass reference crop evapotranspiration (ET0) and compares the performance of ANNs with the conventional method (Penman–Monteith). The use of ANNs was examined number of hidden layers and the activation function were also tested. The best ANN architecture for estimation of daily ET0 was obtained for different data set for Nubaria. Using these data, the networks were trained with daily climatic data (maximum and minimum temperature, dew point and wind speed) as input and the Penman– Monteith (PM) estimated ET0 as output. The analysis was carried out with MATLAB software. Feed forward one-layer networks with sigmoid function were used. Performance evaluation of the models have been carried out by calculating root mean square error (RMSE), The network were selected based on maximized R and R2 value and minimized RMSE values which were 0.98, 0.957 and 0.44 mm/day, respectively in testing. The optimal ANN (4-12-1) for Nubaria regions showed a satisfactory performance in the ET0 estimation. These ANN models may therefore be adopted for estimating ET0 in the study area with reasonable degree of accuracy. | ||
| Keywords | ||
| Reference Evapotranspiration; Penman-Monteith Method; Artificial Neural Network; Back- propagation Algorithm; Training; Testing | ||
|
Statistics Article View: 449 PDF Download: 776 |
||
