Canopy Temperature Estimation Using Gene Expression Programming Models and Artificial Neural Networks

Canopy temperature (Tc) is one of the essential for irrigation scheduling. Measuring canopy temperature is expensive and time-consuming. Simple approaches such as soft computing can be a good tool for this purpose because there has been no documented research in this field. In this study, the ANN (MLP with two hidden layers) and GEP models were used to estimate Tc using limited data such as the dry (Ta) and wet bulb (TW) temperatures, saturation vapor pressure (es), actual vapor pressure (ea), and the vapor-pressure deficit (VPD). Six combinations of input variables were investigated. The perfect model was selected based on statistical indices during the training and testing. Results showed that the performance of the models were influenced by the number of the input variables. The MLP models outperformed GEP models during the training and testing processes. The MLP7 (input variables: es and ea) with MSE of 1.08 °C, RMSE of 1.04 °C, and R2 of 0.92 in the training phase and MSE of 1.02, RMSE of 1.00, and R2 of 0.95 in the validation phase was selected as the perfect model among MLP models. The GEP11(input variables: Ta, TW, es, ea, and VPD) with MSE of 1.32, RMSE of 1.15, and R2 of 0.89 in the training phase and MSE of 0.91, RMSE of 0.95, and R2 of 0.95 in the validation phase was also the perfect model among GEP models. Accordingly, the proposed GEP and MLP models can be drawn on as a perfect model for estimating TC.