The Efficiency of Supporting Machine Models and Planning of Gene Expression in Saffron Crop Yawning

Due to the sensitivity of saffron yield and its effect on climatic parameters and nonlinear properties of plant functions, in this research, saffron yield prediction was considered. The purpose of this study was to evaluate the ability of the support vector machine simulation model (lssvm) and genome genotype programming model (GenXproTools5.0) to predict saffron yield based on meteorological data (minimum temperature, maximum temperature, precipitation, evaporation and relative humidity, Performance one year ago) on a seasonal scale between 1992 and 2006. The best model was selected based on R2, RMSE and MAE assessment criteria. The results showed that in both scenarios, in the H scenario (average winter temperature, mean precipitation in autumn, winter rainfall average, winter evaporation average, yield one year ago), better results were obtained from saffron yield. In the LSSVM model, combinations with the Liner kernel function had more accurate results. But between lssvm model and GEP model, GEP model had higher R2 and lower RMSE and MAE. The R2, RMSE and MAE ratios in this model under the H-scenario in education section were 0.60688, 0.43265 and 0.46432 respectively. In general, the GEP model had more accurate results in saffron yield estimates than the LSSVM model.