In order to find a simplified calculation model for the reference crop evapotranspiration （ET0） in Jiangxi province，the model with the highest accuracy was obtained only with temperature data.This paper was based on daily weather data from 1961 to 2017 in 5 stations in Jiangxi province.We calculated daily ET0data with Penman-Monteith（PM）model，Extreme Learning Machine（ELM）model，Support Vector Machine（SVM）model，Random Forest Model（RF）model，M5 Tree（M5T）model，and Hargreaves（HS）model.The relative root mean square error（RMSE），the decision coefficient（R2）and the model efficiency coefficient（Ens）were used as the evaluation index system to compare the calculation accuracy of different models.The results showed that：the slope of the ELM model ET0daily value fitting equation is 0.973～1.151，which is closest to the standard value“1”.ELM model has the lowest error and highest consistency.The model can be used as the ET0standard calculation model in Jiangxi province.