干旱区生态环境知识资源中心(Arid): Characterizing soil salinity at multiple depth using electromagnetic induction and remote sensing data with random forests: A case study in Tarim River Basin of southern Xinjiang, China

Arid

DOI	10.1016/j.scitotenv.2020.142030
	Characterizing soil salinity at multiple depth using electromagnetic induction and remote sensing data with random forests: A case study in Tarim River Basin of southern Xinjiang, China
	Wang, Fei; Yang, Shengtian; Wei, Yang; Shi, Qian; Ding, Jianli
通讯作者	Ding, JL
来源期刊	SCIENCE OF THE TOTAL ENVIRONMENT
ISSN	0048-9697
EISSN	1879-1026
出版年	2021
卷号	754
英文摘要	Tarim River Basin is experiencing heavy soil degeneration in a long term because of the extreme natural conditions, added with improper human activities such as reclamation and rejected field repeatedly, which hindered the soil health. One of the mainly form is soil salinization. Spatial distribution and variation of soil salinity is essential both for agricultural resource management and local economic development. However, knowledge of the spatial distribution of soil salinization in this region has not been updated since 1980s while land use and climate have undergone major changed. Electromagnetic induction (EMI) has been successfully used to directly measurement the spatial distribution of targeting soil property at field- scale, and apparent electrical conductivity (ECa, mS m(-1)) has become a surrogate of soil salinity (EC, dS m(-1)) studied by many researchers at local scale. However, the effectiveness of this equipment has not been verified in the typical soil salinization areas in southern Xinjiang, especially on a large scale. This study was aimed to test the performance of ECa jointed with Random Forest (RF) for soil salinity regional-scale mapping at a typical arid area, taking Tarim River Basin as an example. The result showed that ECa together with environmental derivative variables and with RF were suited for regional-scale soil salinity mapping. Predicted accuracy of EC was higher at surface (0-20 cm, R-2 = 0.65, RMSE = 5.59) and deeper soil depth (60-80 cm, R-2 = 0.63, RMSE = 2.00, and 80-100 cm, R-2 = 0.61, RMSE = 1.73), lower at transitional zone (20-40 cm, R-2 = 0.55, RMSE = 2.66, and 40-60 cm, R-2 = 0.51, RMSE = 2.49). When ECa is involved in modeling, the prediction accuracy of multiple depths of EC is improved by 13.33%-61.54%, of which the most obvious depths are 60-80 cm and 0-20 cm. The results of variable importance show that SoilGrids were also favored the power EC model. Hence, we strongly recommended to joint EMI reads with remote sensing imagery for soil salinity monitoring at large scale in southern Xinjiang. These EC and ECa map can provide a data source for environmental modeling, a benchmark against which to evaluate and monitor water and salt dynamics, and a guide for the design of future soil surveys. (C) 2020 Elsevier B.V. All rights reserved.
英文关键词	Soil salinity Electromagnetic induction (EMI) Digital soil mapping Random forest Harmonized World Soil Database Tarim River Basin
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000593904200003
WOS关键词	APPARENT ELECTRICAL-CONDUCTIVITY ; WATER CONTENT ; SPATIAL-DISTRIBUTION ; SEMIARID REGION ; MOISTURE ; CLASSIFICATION ; COMBINATION ; PREDICTION ; DYNAMICS ; PATTERNS
WOS类目	Environmental Sciences
WOS研究方向	Environmental Sciences & Ecology
来源机构	北京师范大学 ; 新疆大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/328036
作者单位	[Wang, Fei; Yang, Shengtian; Wei, Yang; Ding, Jianli] Xinjiang Univ, Coll Resource & Environm Sci, Xinjiang Common Univ Key Lab Smart City & Environ, Urumqi 830046, Peoples R China; [Yang, Shengtian] Beijing Normal Univ, Coll Water Sci, Beijing Key Lab Urban Hydrol Cycle & Sponge City, Beijing 100875, Peoples R China; [Shi, Qian] Sun Yat Sen Univ, Sch Geog & Planning, West Xingang Rd, Guangzhou 510275, Peoples R China; [Shi, Qian] Sun Yat Sen Univ, Guangdong Key Lab Urbanizat & Geosimulat, West Xingang Rd, Guangzhou 510275, Peoples R China
推荐引用方式 GB/T 7714	Wang, Fei,Yang, Shengtian,Wei, Yang,et al. Characterizing soil salinity at multiple depth using electromagnetic induction and remote sensing data with random forests: A case study in Tarim River Basin of southern Xinjiang, China[J]. 北京师范大学, 新疆大学,2021,754.
APA	Wang, Fei,Yang, Shengtian,Wei, Yang,Shi, Qian,&Ding, Jianli.(2021).Characterizing soil salinity at multiple depth using electromagnetic induction and remote sensing data with random forests: A case study in Tarim River Basin of southern Xinjiang, China.SCIENCE OF THE TOTAL ENVIRONMENT,754.
MLA	Wang, Fei,et al."Characterizing soil salinity at multiple depth using electromagnetic induction and remote sensing data with random forests: A case study in Tarim River Basin of southern Xinjiang, China".SCIENCE OF THE TOTAL ENVIRONMENT 754(2021).