Improving model performance in mapping cropland soil organic matter using time-series remote sensing data  

作　　者：Xianglin Zhang Jie Xue Songchao Chen Zhiqing Zhuo Zheng Wang Xueyao Chen Yi Xiao Zhou Shi 

机构地区：[1]Institute of Applied Remote Sensing and Information Technology,College of Environmental and Resource Sciences,Zhejiang University,Hangzhou 310058,China [2]Department of Land Management,Zhejiang University,Hangzhou 310058,China [3]ZJU-Hangzhou Global Scientific and Technological Innovation Center,Zhejiang University,Hangzhou 311215,China [4]Institute of Digital Agriculture,Zhejiang Academy of Agricultural Sciences,Hangzhou 310021,China [5]Key Laboratory of Spectroscopy Sensing,Ministry of Agriculture and Rural Affairs,Hangzhou 310058,China

出　　处：《Journal of Integrative Agriculture》2024年第8期2820-2841,共22页农业科学学报（英文版）

基　　金：the National Natural Science Foundation of China(U1901601);the National Key Research and Development Program of China(2022YFB3903503)。

摘　　要：Faced with increasing global soil degradation,spatially explicit data on cropland soil organic matter(SOM)provides crucial data for soil carbon pool accounting,cropland quality assessment and the formulation of effective management policies.As a spatial information prediction technique,digital soil mapping(DSM)has been widely used to spatially map soil information at different scales.However,the accuracy of digital SOM maps for cropland is typically lower than for other land cover types due to the inherent difficulty in precisely quantifying human disturbance.To overcome this limitation,this study systematically assessed a framework of“information extractionfeature selection-model averaging”for improving model performance in mapping cropland SOM using 462 cropland soil samples collected in Guangzhou,China in 2021.The results showed that using the framework of dynamic information extraction,feature selection and model averaging could efficiently improve the accuracy of the final predictions(R^(2):0.48 to 0.53)without having obviously negative impacts on uncertainty.Quantifying the dynamic information of the environment was an efficient way to generate covariates that are linearly and nonlinearly related to SOM,which improved the R^(2)of random forest from 0.44 to 0.48 and the R^(2)of extreme gradient boosting from 0.37to 0.43.Forward recursive feature selection(FRFS)is recommended when there are relatively few environmental covariates(<200),whereas Boruta is recommended when there are many environmental covariates(>500).The Granger-Ramanathan model averaging approach could improve the prediction accuracy and average uncertainty.When the structures of initial prediction models are similar,increasing in the number of averaging models did not have significantly positive effects on the final predictions.Given the advantages of these selected strategies over information extraction,feature selection and model averaging have a great potential for high-accuracy soil mapping at any scales,so this approach can provide m

关 键 词：CROPLAND soil organic matter digital soil mapping machine learning feature selection model averaging 

分 类 号：S159-3[农业科学—土壤学]