Hybrid Statistical and Machine Learning Methods for Daily Evapotranspiration Modeling

Machine learning (ML) models, including artificial neural networks (ANN), generalized regression (GRNN), and adaptive neuro-fuzzy interface systems (ANFIS), have received considerable attention for their ability to provide accurate predictions in various problem domains. However, these models may produce inconsistent results when solving linear problems. To overcome this limitation, paper proposes hybridizations of ML autoregressive integrated moving average (ARIMA) a more general forecasting model evapotranspiration (ET0). The proposed are developed tested using daily ET0 data collected over 11 years (2010–2020) the Samsun province Türkiye. show that ARIMA–GRNN reduces root mean square error by 48.38%, ARIMA–ANFIS 8.56%, ARIMA–ANN 6.74% compared traditional ARIMA model. Consequently, integration with can offer dependable prediction ET0, which be beneficial many branches such as agriculture water management require estimations.