High‐resolution reference evapotranspiration for arid Egypt: Comparative analysis and evaluation of empirical and artificial intelligence models

Accurate estimation of evapotranspiration has crucial importance in arid regions like Egypt, which suffers from the scarcity precipitation and water shortages. This study provides an investigation performance 31 widely used empirical equations 20 models developed using five artificial intelligence (AI) algorithms to estimate reference (ET0) generate gridded high-resolution daily ET0 estimates over Egypt. The AI include support vector machine-radial basis function (SVM-RBF), random forest (RF), group method data handling neural network (GMDH-NN), multivariate adaptive regression splines (MARS), dynamic evolving fuzzy interference system (DENFIS). Daily observations records 41 stations distributed Egypt were calculate FAO56 Penman–Monteith equation as a estimate. multiparameter Kling-Gupta efficiency (KGE) metric was evaluation for its robustness representing different statistical error/agreement characteristics single value. By category, based on radiation performed better replicating FAO56-PM followed by temperature- mass-transfer-based ones. Ritchie found be best overall (median KGE 0.76) Caprio 0.64), Penman 0.52) station-wise ranking. On other hand, RF model, having maximum minimum temperatures, wind speed, relative humidity predictors, outperformed algorithms. Overall, model among all equations. generated 0.10° × enabled detection significant increase 0.12–0.16 mm·decade−1 agricultural-dependent Nile Delta modified Mann–Kendall test Sen's slope estimator.