Evapotranspiration represents the water requirement of plants during their growing season, and its accurate measurement at the farm is essential for agricultural water planners and managers. Field measurements of evapotranspiration have always been associated with many difficulties that have led researchers to seek a way to remotely measure this component in horticultural and agricultural areas. This study aims to investigate an indirect approach for daily rice crop evapotranspiration (ETc) measurement by machine learning (ML) techniques and the least available climatic variables. For this purpose, daily meteorological variables were obtained from three ground meteorological stations in rice cultivation regions of northern Iran during 2003–2016. The ETc rates were calculated by seven meteorological variables, the FAO‐56 Penman‐Monteith equation, and the regional calibrated rice crop coefficient and considered as the reference data. The MLs, including Multilayer Perceptron (MLP), Radial Basis Function (RBF), Generalized Regression Neural Network (GRNN), and Group Method of Data Handling (GMDH), were utilized for ETc modeling. Different input combinations were applied, based on the use of minimum effective variables as input. Results showed that the models showed the most accurate performances in the input combination of four climatic variables: sunshine duration, maximum temperature, relative humidity, and wind speed. Investigating the accuracy of models in rice growth phases showed that the least estimation error belonged to the initial growing stage, which increased during the mid‐season and late‐season growing stages. A comparison of the models showed that the GMDH model performed better against the other competitors. For this model, both the Nash‐Sutcliffe (NS) coefficient and R2 were greater than 0.98, and the Root Mean Square Error (RMSE) ranged between 0.214 and 0.234 mm per day in all stations. The current approach showed promising results in rice evapotranspiration modeling by only four common meteorological variables and can be reliably applied for indirect measurement of this variable over the rice farms. The studied approach will have research value for rice and other crops in similar/different climatic conditions.