Loading...
Please wait, while we are loading the content...
Similar Documents
Modelling Soil Temperature by Tree-Based Machine Learning Methods in Different Climatic Regions of China
| Content Provider | MDPI |
|---|---|
| Author | Dong, Jianhua Huang, Guomin Wu, Lifeng Liu, Fa Li, Sien Cui, Yaokui Wang, Yicheng Leng, Menghui Wu, Jie Wu, Shaofei |
| Copyright Year | 2022 |
| Description | Accurate estimation of soil temperature $(T_{s}$) at a national scale under different climatic conditions is important for soil–plant–atmosphere interactions. This study estimated daily $T_{s}$ at the 0 cm depth for 689 meteorological stations in seven different climate zones of China for the period 1966–2015 with the M5P model tree (M5P), random forests (RF), and the extreme gradient boosting (XGBoost). The results showed that the XGBoost model (averaged coefficient of determination $(R^{2}$) = 0.964 and root mean square error (RMSE) = 2.066 °C) overall performed better than the RF (averaged $R^{2}$ = 0.959 and RMSE = 2.130 °C) and M5P (averaged $R^{2}$ = 0.954 and RMSE = 2.280 °C) models for estimating $T_{s}$ with higher computational efficiency. With the combination of mean air temperature $(T_{mean}$) and global solar radiation $(R_{s}$) as inputs, the estimating accuracy of the models was considerably high (averaged $R^{2}$ = 0.96–0.97 and RMSE = 1.73–1.99 °C). On the basis of $T_{mean}$, adding $R_{s}$ to the model input had a greater degree of influence on model estimating accuracy than adding other climatic factors to the input. Principal component analysis indicated that soil organic matter, soil water content, $T_{mean}$, relative humidity (RH), $R_{s}$, and wind speed $(U_{2}$) are the main factors that cause errors in estimating $T_{s}$, and the total error interpretation rate was 97.9%. Overall, XGBoost would be a suitable algorithm for estimating $T_{s}$ in different climate zones of China, and the combination of $T_{mean}$ and $R_{s}$ as model inputs would be more practical than other input combinations. |
| Starting Page | 5088 |
| e-ISSN | 20763417 |
| DOI | 10.3390/app12105088 |
| Journal | Applied Sciences |
| Issue Number | 10 |
| Volume Number | 12 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2022-05-18 |
| Access Restriction | Open |
| Subject Keyword | Applied Sciences Remote Sensing Soil Temperature Machine Learning Models Climatic Zones Extreme Gradient Boosting Principal Components Analysis |
| Content Type | Text |
| Resource Type | Article |
