? An integrated method of selecting environmental covariates for predictive soil depth mapping
Quick Search in JIA      Advanced Search  
    2019, Vol. 18 Issue (02): 301-315     DOI: 10.1016/S2095-3119(18)61936-7
Special focus: Digital mapping in agriculture and environment Current Issue | Next Issue | Archive | Adv Search  |   
An integrated method of selecting environmental covariates for predictive soil depth mapping
LU Yuan-yuan1, 2, LIU Feng1, ZHAO Yu-guo1, 2, SONG Xiao-dong1, ZHANG Gan-lin1, 2 
1 State Key Laboratory of Soil and Sustainable Agriculture, Institute of Soil Science, Chinese Academy of Sciences, Nanjing 210008, P.R.China
2 University of Chinese Academy of Sciences, Beijing 100049, P.R.China
 Download: PDF in ScienceDirect (20438 KB)   HTML (1 KB)   Export: BibTeX | EndNote (RIS)      Supporting Info
Environmental covariates are the basis of predictive soil mapping.  Their selection determines the performance of soil mapping to a great extent, especially in cases where the number of soil samples is limited but soil spatial heterogeneity is high.  In this study, we proposed an integrated method to select environmental covariates for predictive soil depth mapping.  First, candidate variables that may influence the development of soil depth were selected based on pedogenetic knowledge.  Second, three conventional methods (Pearson correlation analysis (PsCA), generalized additive models (GAMs), and Random Forest (RF)) were used to generate optimal combinations of environmental covariates.  Finally, three optimal combinations were integrated to produce a final combination based on the importance and occurrence frequency of each environmental covariate.  We tested this method for soil depth mapping in the upper reaches of the Heihe River Basin in Northwest China.  A total of 129 soil sampling sites were collected using a representative sampling strategy, and RF and support vector machine (SVM) models were used to map soil depth.  The results showed that compared to the set of environmental covariates selected by the three conventional selection methods, the set of environmental covariates selected by the proposed method achieved higher mapping accuracy.  The combination from the proposed method obtained a root mean square error (RMSE) of 11.88 cm, which was 2.25–7.64 cm lower than the other methods, and an R2 value of 0.76, which was 0.08–0.26 higher than the other methods.  The results suggest that our method can be used as an alternative to the conventional methods for soil depth mapping and may also be effective for mapping other soil properties.
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
Articles by authors
LU Yuan-yuan
LIU Feng
ZHAO Yu-guo
SONG Xiao-dong
ZHANG Gan-lin
Key wordsenvironmental covariate selection     integrated method     predictive soil mapping     soil depth     
Received: 2017-12-21; Accepted: 2018-03-27
Fund: The study was supported financially by the National Natural Science Foundation of China (91325301, 41571212 and 41137224), the Project of “One-Three-Five” Strategic Planning & Frontier Sciences of the Institute of Soil Science, Chinese Academy of Sciences (ISSASIP1622), and the National Key Basic Research Special Foundation of China (2012FY112100).
Corresponding Authors: Correspondence ZHANG Gan-lin, Tel: +86-25-86881279, E-mail: glzhang@issas.ac.cn    
About author: LU Yuan-yuan, E-mail: exlimit00@qq.com;
Cite this article:   
LU Yuan-yuan, LIU Feng, ZHAO Yu-guo, SONG Xiao-dong, ZHANG Gan-lin. 2019. An integrated method of selecting environmental covariates for predictive soil depth mapping. Journal of Integrative Agriculture, 18(02): 301-315.
http://www.chinaagrisci.com/Jwk_zgnykxen/EN/ 10.1016/S2095-3119(18)61936-7      or     http://www.chinaagrisci.com/Jwk_zgnykxen/EN/Y2019/V18/I02/301
No references of article
[1] YANG Xin-ran, Kevin Z. Chen, KONG Xiang-zhi. Factors affecting the adoption of on-farm milk safety measures in Northern China - An examination from the perspective of farm size and production type[J]. Journal of Integrative Agriculture, 2019, 18(02): 471-481.
Copyright © 2015 ChinaAgriSci.com, All Rights Reserved
Chinese Academy of Agricultural Sciences (CAAS) No. 12 South Street, Zhongguancun, Beijing 100081, P. R. China
http://www.ChinaAgriSci.com   JIA E-mail: jia_journal@caas.cn