Iran is currently facing a severe water crisis, with the agricultural sector accounting for more than 90% of total water consumption. Therefore, accurate estimation of reference evapotranspiration (ET₀) is essential for efficient irrigation planning and sustainable water resources management, particularly in arid and semi-arid regions. This study evaluates and compares the performance of several machine learning and hybrid models for monthly ET₀ prediction at the Ahvaz synoptic station located in Khuzestan Province, southwestern Iran. Monthly meteorological data, including maximum and minimum air temperature (Tmax, Tmin), mean air temperature (Tmean), dew point temperature, relative humidity (maximum, minimum, and mean), wind speed, sunshine hours, and precipitation, were collected for the period 2007–2023.Reference evapotranspiration values were calculated using the FAO-56 Penman–Monteith method. Five predictive models were developed and assessed, including Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), Wavelet-Artificial Neural Network (WANN), Support Vector Machine (SVM), and Decision Tree (DT). The dataset was divided into training (80%) and testing (20%) subsets, and model performance was evaluated using the coefficient of determination (R²), Root Mean Square Error (RMSE), and Mean Bias Error (MBE). The results indicated that the hybrid WANN model achieved the highest prediction accuracy, with R² = 0.912, RMSE = 1.940, and MBE = +0.05, outperforming the other models. The LSTM model ranked second (R² = 0.895), followed by ANN (R² = 0.878), whereas the DT model showed the weakest predictive performance (R² = 0.812). The superior performance of WANN demonstrates the capability of wavelet-based hybrid approaches in capturing nonlinear and seasonal patterns of ET₀ under extremely hot climatic conditions. The findings suggest that the WANN model can serve as an effective tool for monthly ET₀ prediction and may support irrigation scheduling, drought management, and climate adaptation strategies in Khuzestan Province and other arid regions.