文献类型： 外文期刊

作者： Zhang, Xianglin ¹ ; Chen, Songchao ¹ ; Xue, Jie ³ ; Wang, Nan ² ; Xiao, Yi ² ; Chen, Qianqian ² ; Hong, Yongsheng ² ; Zhou, Yin ⁴ ; Teng, Hongfen ⁵ ; Hu, Bifeng ⁶ ; Zhuo, Zhiqing ⁷ ; Ji, Wenjun ⁸ ; Huang, Yuanfang ⁸ ; Gou, Yuxuan ⁸ ; Richer-de-Forges, Anne C. ⁹ ; Arrouays, Dominique ⁹ ; Shi, Zhou ² ;

作者机构： 1.ZJU Hangzhou Global Sci & Technol Innovat Ctr, Hangzhou 311200, Peoples R China

2.Zhejiang Univ, Inst Appl Remote Sensing & Informat Technol, Coll Environm & Resource Sci, Hangzhou 310058, Peoples R China

3.Zhejiang Univ, Dept Land Management, Hangzhou 310058, Peoples R China

4.Zhejiang Univ Finance & Econ, Inst Land & Urban Rural Dev, Hangzhou 310018, Peoples R China

5.Wuhan Inst Technol, Sch Environm Ecol & Biol Engn, Wuhan 430205, Peoples R China

6.Jiangxi Univ Finance & Econ, Sch Tourism & Urban Management, Dept Land Resource Management, Nanchang 330013, Peoples R China

7.Zhejiang Acad Agr Sci, Inst Digital Agr, Hangzhou 310021, Peoples R China

8.China Agr Univ, Coll Land Sci & Technol, Beijing 100193, Peoples R China

9.INRAE, Unite InfoSol, F-45075 Orleans, France

关键词： Digital soil mapping; Variable selection; Quantile regression forests; Computation efficiency; Northeast and North China

期刊名称：GEODERMA （ 影响因子：6.1； 五年影响因子：7.0 ）

ISSN： 0016-7061

年卷期： 2023 年 432 卷

页码：

收录情况： SCI

摘要： In the context of increasing soil degradation worldwide, spatially explicit soil information is urgently needed to support decision-making for sustaining limited soil resources. Digital soil mapping (DSM) has been proven as an efficient way to deliver soil information from local to global scales. The number of environmental covariates used for DSM has rapidly increased due to the growing volume of remote sensing data, therefore variable selection is necessary to deal with multicollinearity and improve model parsimony. Compared with Boruta, recursive feature elimination (RFE), and variance inflation factor (VIF) analysis, we proposed the use of modified greedy feature selection (MGFS), for DSM regression. For this purpose, using quantile regression forest, 402 soil samples and 392 environmental covariates were used to map the spatial distribution of soil organic carbon density (SOCD) in Northeast and North China. The result showed that MGFS selected the most parsimonious model with only 9 covariates (e.g., brightness index, mean annual temperature), much lower than RFE (22 covariates), VIF (30 covariates), and Boruta (76 covariates). The repeated validation (50 times) showed that the MGFS derived model performed better (R2 of 0.60, LCCC of 0.74, RMSE of 13.80 t ha -1) than these using full covariates, Boruta, RFE and VIF (R2 of 0.48-0.57, LCCC of 0.64-0.72, RMSE of 14.24-15.79 t ha -1). Despite the similar performance of the uncertainty estimate (PICP), the model using MGFS and RFE had the lowest global uncertainty (0.86) as indicated by the uncertainty index. In addition, MGFS had the best computation efficiency when considering the steps of variable selection and map prediction. Given these advantages over Boruta, RFE and VIF, MGFS has a high potential in fine-resolution soil mapping practices, especially for these studies at a broad scale involving heavy computation on millions or billions of pixels.