Generalized Daily Reference Evapotranspiration Models Based on a Hybrid Optimization Algorithm Tuned Fuzzy Tree Approach

Reference evapotranspiration (ET0) is an important driver in managing scarce water resources and making decisions on real-time future irrigation scheduling. Therefore, accurate prediction of ET0 crucial the management discipline. In this study, was performed by employing several optimization algorithms tuned Fuzzy Inference System (FIS) Tree (FT) models, for first time, whose generalization capability tested using data from other stations. The FISs FTs were developed through parameters tuning Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Pattern Search (PS), their combinations. FT combining FIS objects that received ranked meteorological variables. A total 50 models model ranking utilizing Shannon’s Entropy (SE). Evaluation outcomes revealed superiority hybrid PSO-GA Sugeno type 1 (with R = 0.929, NRMSE 0.169, accuracy 0.999, NS 0.856, IOA 0.985) over others. For evaluating best model, three different parts datasets (all-inclusive, 1st half, 2nd half) five test stations evaluated. proposed similarly well, according to findings, study concluded approach, which composed standalone objects, suitable predicting daily values.