Upscaling plot-scale soil respiration in winter wheat and summer maize rotation croplands in Julu County,North China |
| |
| Institution: | 1. World Agroforestry Centre (ICRAF), West and Central Africa, BP 16317 Yaoundé, Cameroon;2. World Agroforestry Centre, West and Central Africa, Sahel Node, BP E 5115 Bamako, Mali;3. World Agroforestry Centre (ICRAF), P.O. Box 30677-00100 GPO, Nairobi, Kenya;4. Dept. Environment, Instituto Nacional de Investigación y Tecnología Agraria y Alimentaria (I.N.I.A.), Ctra. de A Coruña 7.5, 28040 Madrid, Spain;5. World Agroforestry Centre (ICRAF), Avenue Jean-Mermoz, 28 BP 2823 Abidjan, Côte d''ivoire |
| |
| Abstract: | Soil respiration (Rs) data from 45 plots were used to estimate the spatial patterns of Rs during the peak growing seasons of winter wheat and summer maize in Julu County, North China, by combining satellite remote sensing data, field-measured data, and a support vector regression (SVR) model. The observed Rs values were well reproduced by the model at the plot scale, with a root-mean-square error (RMSE) of 0.31 μmol CO2 m?2 s?1 and a coefficient of determination (R2) of 0.73. No significant difference was detected between the prediction accuracy of the SVR model for winter wheat and summer maize. With forcing from satellite remote sensing data and gridded soil property data, we used the SVR model to predict the spatial distributions of Rs during the peak growing seasons of winter wheat and summer maize rotation croplands in Julu County. The SVR model captured the spatial variations of Rs at the county scale. The satellite-derived enhanced vegetation index was found to be the most important input used to predict Rs. Removal of this variable caused an RMSE increase from 0.31 μmol CO2 m?2 s?1 to 0.42 μmol CO2 m?2 s?1. Soil properties such as soil organic carbon (SOC) content and soil bulk density (SBD) were the second most important factors. Their removal led to an RMSE increase from 0.31 μmol CO2 m?2 s?1 to 0.37 μmol CO2 m?2 s?1. The SVR model performed better than multiple regression in predicting spatial variations of Rs in winter wheat and summer maize rotation croplands, as shown by the comparison of the R2 and RMSE values of the two algorithms. The spatial patterns of Rs are better captured using the SVR model than performing multiple regression, particularly for the relatively high and relatively low Rs values at the center and northeast study areas. Therefore, SVR shows promise for predicting spatial variations of Rs values on the basis of remotely sensed data and gridded soil property data at the county scale. |
| |
| Keywords: | Soil respiration Support vector regression Landsat 8 Soil property Winter wheat and summer maize rotation |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
