The methane emission data of paddy fields was obtained by using the static chamber and gas chromatography, and six parameters including atmospheric temperature, soil temperature at 5 cm depth, pH of soil, Eh of soil, soil moisture and ground biomass were selected as the primary influencing factors of methane emission. The support vector regression (epsilon-SVR) model was built on the optimization of structural risk minimization, and the parameters of the epsilon-SVR model were optimized using Leave-one-out Cross Validation (LOOCV). The prediction accuracy of model was evaluated by k-fold cross validation with the mean relative error (MRE) and the root mean square error (RMSE). In addition, the accuracy of the epsilon-SVR model was analyzed by comparison with the Back Propagation-Artificial Neural Network (BP-ANN) model. The results indicated that the predicted value of the epsilon-SVR model with the parameters C and epsilon optimized by LOOCV was in good agreement with the measured value, and the average MRE of test samples was 44% and the average RMSE was 16.21 mg x (m2 x h)(-1) in the process of 11-fold cross validation. Compared with the BP-ANN model, the correlation coefficient was 0.863, and all the indicators were better. It demonstrated that the 8-SVR model could be applied to the prediction of methane emission of paddy fields.