Machine Learning-Based Estimation of Daily Reference Evapotranspiration in Vojvodina, Serbia

Reference evapotranspiration (ET0) is most commonly estimated using the FAO-56 Penman-Monteith (PM) equation. However, its application is often limited by the lack of required meteorological parameters. Due to their flexibility, ability to operate with limited input, and high accuracy in estimating ET0, machine learning models have become increasingly relevant in scientific research, offering a practical alternative under limited data conditions. In this study, artificial neural networks (ANNs) were applied to estimate daily ET0 using meteorological data from the Novi Sad station in Vojvodina (Serbia). The dataset consisted of eight meteorological variables relevant to evapotranspiration processes. Analysis showed that some variables had a stronger influence on ET0 prediction than others. To evaluate their combined effect, a series of ANN models with different input combinations was developed and tested. The FAO-56 PM method was used as a benchmark, and model performance was evaluated using R2, NSE, RMSE, and MAE. The highest accuracy was achieved when all variables were included, providing the model with maximum information. The best performance was obtained using a two-hidden-layer architecture with 32 and 16 neurons, resulting in R2 = 0.98, NSE = 97.86%, RMSE = 0.25 mm day-1, and MAE = 0.17 mm day-1.