Abstract: To study the applicability of ET₀ estimation methods for different reference crops in Jiangsu area, meteorological data was collected from January 1957 to December 2019 in Xuzhou site, Gaoyou site, and Kunshan site, Jiangsu Province were collected, and 12 different models were used to estimate the reference crop evapotranspiration（ET₀） at each site were used. Among the estimation models, Priestly-Taylor, Hansen, Jensen-Haise and Makkink were modeled based on radiation. MC-Cloud, 1985 Hargreaves and Thornthwaite were based on temperature. Copais, Valiantzas 1 and Valiantzas 2 were integrated methods. SVM and XGBoost were machine learning models. The calculated values of 12 models for estimating ET₀ were compared with the Penman-Monteith model（PM）. The results show that the SVM model has the highest GPI（comprehensive evaluation index） value of the three sites. With the same input parameters, the simulation accuracy of the machine learning model is better than that of Priestley-Taylor and Makkink models in the synthesis method, the temperature method, and the radiation method. As the input parameters of machine learning model decrease, the simulation accuracy of the machine learning model decreases in turn. The above research results can provide a scientific basis for estimating ET₀ when the meteorological data in Jiangsu area are imperfect.