Performance Evaluation of ETo Prediction Methods: Dispersion Analysis and Accuracy Criteria Across Time Intervals

Accurate forecasting of reference evapotranspiration (ETo) is crucial for sustainable water resource management and precision agriculture. The present study evaluates three ETo prediction methods: Random Forest (RF), Cartesian Genetic Programming (CGP), and Convolutional Neural Network-Graphics Processing Unit (CNN-GPU) across time intervals of 1 to 364 days. Using dispersion analysis (scatter/violin plots) and accuracy metrics (RMSE, MAE, R^2, SI), it was seen that the RF and CNN-GPU models consistently outperform CGP, particularly at extended horizons. At 364 days, CNN-GPU achieved the highest accuracy (RMSE: 0.678 mm/day, R^2: 0.874), while RF maintained robust performance (RMSE: 0.683 mm/day, R^2: 0.872) and minimal dispersion (SI: 0.244--0.278). In contrast, CGP exhibited slightly higher error indices (RMSE: 0.702mm/day) and greater variability. Statistical validation via t-tests, F-tests, and ANOVA revealed significant differences in performance, especially at longer lags (p < 0.05), with CNN-GPU often showing superior accuracy. Time-series analyses further confirmed that RF and CNN-GPU effectively capture seasonal ETo trends, while CGP struggles with increased lag.