Employing Data Mining Algorithms and Mathematical Empirical Models for Predicting Wind Drift and Evaporation Losses of a Sprinkler Irrigation Method

The advantage of a sprinkler irrigation method is that it saves up to 50% water consumption during the application water, as compared any other surface system. To assess behavior method, wind drift and evaporation losses (WDEL) are often employed important parameters. predictive capacities four previous mathematical empirical models two data mining algorithms, namely, reduced-error pruning tree (REPTree) artificial neural network (ANN) models, were evaluate impact operating parameters on WDEL. inputs REPTree ANN working pressure, vapor pressure deficit, air temperature, speed, nozzle diameter, relative humidity. In experimental field, for collection, solid set sprinklers collectors positioned per ASAE standards was employed. Promising results showed remarkable performance one tested, with confidence index value 0.829. Meanwhile, presented smaller errors testing qualified use given their values 0.956 0.964, respectively. algorithms classified optimal indicating alone inadequate in operational situations involving variables.