| Autor: |
Qiang, Chen, Wei-Guo, Jiang, Xi, Chen, Li-Hua, Yuan, Wen-Jie, Wang, Ying-Zi, Pan, Wei, Wang, Xiao-Fu, Liu, Hai-Jiang, Liu |
| Rok vydání: |
2013 |
| Předmět: |
|
| Zdroj: |
Huan jing ke xue= Huanjing kexue. 34(8) |
| ISSN: |
0250-3301 |
| Popis: |
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. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
