Examination of Single- and Hybrid-Based Metaheuristic Algorithms in ANN Reference Evapotranspiration Estimating

Hydrological resource management, including crop watering and irrigation scheduling, relies on reliable estimates of reference evapotranspiration (ETo). However, previous studies forecasting ETo have not dealt with comparing single hybrid metaheuristic algorithms in much detail. This study aims to assess the efficiency a novel methodology simulate univariate monthly using an artificial neural network (ANN) integrated particle swarm optimisation–grey wolf optimiser algorithm (PSOGWO). Several state-of-the-art algorithms, constriction coefficient-based optimisation chaotic gravitational search (CPSOCGSA), slime mould (SMA), marine predators (MPA) modified PSO were used evaluate PSOGWO’s prediction accuracy. Monthly meteorological data collected Al-Kut City (1990 2020) for model training, testing validation. The results indicate that pre-processing techniques can improve raw quality may also suggest best predictors scenario. That said, all models be considered efficient acceptable simulation levels. PSOGWO-ANN slightly outperformed other based several statistical tests (e.g., coefficient determination 0.99). findings contribute better management water resources City, agricultural region produces wheat Iraq is under stress climate change.