Hyperspectral inversion of soil heavy metals in Three-River Source Region based on random forest model

doi:10.1016/j.catena.2021.105222

	Hyperspectral inversion of soil heavy metals in Three-River Source Region based on random forest model
	Zhou, Wei 1,2,3; Yang, Han 3; Xie, Lijuan 3; Li, Haoran 3; Huang, Lu 3; Zhao, Yapeng 1; Yue, Tianxiang 1
刊名	CATENA
	2021-07-01
卷号	202 页码:10
关键词	Soil heavy metal Hyperspectral Random forest model (RF) Support vector machine (SVM) Three-River Source Region
ISSN号	0341-8162
DOI	10.1016/j.catena.2021.105222
通讯作者	Zhou, Wei(zhouw866@163.com) ; Yue, Tianxiang(yue@lreis.ac.cn)
英文摘要	Hyperspectral remote sensing technology has considerable research value in monitoring and evaluating soil heavy metal pollution. In this study, the Three-River Source Region was taken as the study area. The occurrence relationship of six heavy metals in soil, such as Mn, Cu, Zn, Pb, Cr, Ni, with soil organic matter, clay minerals, and iron-manganese oxides, was studied through the determination and analysis of soil samples and the collection of soil reflectance spectrum. Spectral transformation was carried out by first derivative, second derivative, inverse-log, continuum removal and multiple scattering correction of the spectrum. The correlation between soil heavy metal content and soil spectrum was analyzed to select the characteristic band, and partial least squares (PLS) method, support vector machine (SVM) method and random forest (RF) model were used to build inversion model based on characteristic band. Then the best combination of spectral transformation and inversion model were explored. The results showed that Pb contents were the twice of the background in Qinghai province. The combination spectrum processing method can improve the correlation between spectrum and heavy metals. The location and quantity of characteristic bands of six heavy metals are different. The accuracy of RF was significantly better than that of SVM and PLS for all six heavy metal (i.e. pb: R-RF(2) = 0.83, R-SVM(2) = 0.62, R-PLS(2) = 0.18), and the model effective of soil properties in non-polluted sites were reliable (i.e. clay: R-RF(2) = 0.93, R-SVM(2) = 0.87, R-PLS(2) = 0.74). This study can provide technical support for the larger-scale monitoring of soil heavy metal content and heavy metal pollution assessment.
资助项目	National Natural Science Foundation of China[41501575] ; National Natural Science Foundation of China[41977337] ; National Natural Science Foundation of China[41590844] ; National Natural Science Foundation of China[41930647] ; China Post-doctoral Science Foundation[2019M650821] ; Scientific and Technological Research Program of Chongqing Municipal Education Commission[KJQN201800702] ; Project of Chongqing Science and Technology Bureau[cstc2019jscx-fxydX0036]
WOS关键词	REFLECTANCE SPECTROSCOPY ; CLASSIFICATION ; CONTAMINATION
WOS研究方向	Geology ; Agriculture ; Water Resources
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000643594100004
资助机构	National Natural Science Foundation of China ; China Post-doctoral Science Foundation ; Scientific and Technological Research Program of Chongqing Municipal Education Commission ; Project of Chongqing Science and Technology Bureau
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/162860]
专题	中国科学院地理科学与资源研究所
通讯作者	Zhou, Wei; Yue, Tianxiang
作者单位	1.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 2.Southwest Univ, Sch Geog Sci, Chongqing 400715, Peoples R China 3.Chongqing Jiaotong Univ, Chongqing 400074, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Wei,Yang, Han,Xie, Lijuan,et al. Hyperspectral inversion of soil heavy metals in Three-River Source Region based on random forest model[J]. CATENA,2021,202:10.
APA	Zhou, Wei.,Yang, Han.,Xie, Lijuan.,Li, Haoran.,Huang, Lu.,...&Yue, Tianxiang.(2021).Hyperspectral inversion of soil heavy metals in Three-River Source Region based on random forest model.CATENA,202,10.
MLA	Zhou, Wei,et al."Hyperspectral inversion of soil heavy metals in Three-River Source Region based on random forest model".CATENA 202(2021):10.