Characterization and Prediction of Wind Drift and Evaporation Loss in Low‐Pressure Sprinkler Fertigation Under Multivariate Meteorological Conditions

ABSTRACT Wind drift and evaporation loss (WDEL) significantly affect the performance of low‐pressure sprinkler irrigation systems. However, research on its characteristics and prediction under integrated water‐fertilizer management remains limited. This study evaluated WDEL variability under diverse meteorological conditions in a low‐pressure sprinkler fertigation system. The effects of operating pressure, fertilizer concentration and meteorological factors on fertigation uniformity and accuracy were investigated, with a focus on losses of fertilizer solution (WDEL F ), water (WDEL W ) and urea fertilizer (WDEL U ). Four machine learning models (multiple linear regression [MLR]; random forest [RF]; support vector regression [SVR]; artificial neural network [ANN]) were compared. The results revealed that WDEL reduced the uniformity coefficient (CU) of the sprinkler by up to 59% under an average wind speed (WS avg ) of 5.5 m s −1 and a vapour pressure deficit (VPD) of 2.20 kPa. VPD impacted WDEL F and WDEL W ( p < 0.01), whereas WS had the most substantial effect on WDEL U ( p < 0.01). SVR achieved the highest determination coefficient ( R 2 = 0.792) for predicting WDEL F , whereas ANN outperformed other methods for WDEL W and WDEL U , with R 2 values of 0.711 and 0.854, respectively. These results provide theoretical support for mitigating WDEL risks and improving water–fertilizer utilization efficiency under low‐pressure sprinkler fertigation.