Reference crop evapotranspiration (ETo) estimation is of importance in irrigation water management for the calculation of crop water requirements and its scheduling, in rainfall‐runoff modeling and in numerous other water resources studies. Due to its importance, several direct and indirect methods have been employed to determine the reference crop evapotranspiration but success has been limited because the direct measurement methods lack in precision and accuracy due to scale issues and other problems, while some of the more accurate indirect methods, e.g., the Penman‐Monteith benchmark model, are time‐consuming and require weather input data that are not routinely monitored. This paper has used the Kohonen self‐organizing map (KSOM), unsupervised artificial neural networks, to predict the ETo. based on observed daily weather data at two climatically diverse basins: a small experimental catchment in temperate Edinburgh, UK and a semiarid lake basin in Udaipur, India. This was achieved by using the powerful clustering capability of the KSOM to analyze the multidimensional data array comprising the estimated ETo (based on the Food and Agricultural Organization (FAO) Penman‐Monteith model) and different subsets of climatic variables known to affect it. The findings indicate that the KSOM‐based ETo estimates even with fewer input variables were in good agreement with those obtained using the conventional FAO Penman‐Monteith formulation employing the full complement of weather data at the two locations. More crucially, the KSOM‐based estimates were also found to be significantly superior to those estimated using currently recommended empirical ETo methods for data scarce situations such as those in developing countries.