干旱区生态环境知识资源中心(Arid): Estimating salt content of vegetated soil at different depths with Sentinel-2 data

Arid

DOI	10.7717/peerj.10585
	Estimating salt content of vegetated soil at different depths with Sentinel-2 data
	Chen, Yinwen; Qin, Yuanlin; Zhang, Zhitao; Zhang, Junrui; Han, Jia; Liu, Dan
通讯作者	Zhang, ZT (corresponding author), Northwest A&F Univ, Coll Water Resources & Architectural Engn, Yangling, Shaanxi, Peoples R China. ; Zhang, ZT (corresponding author), Northwest A&F Univ, Key Lab Agr Soil & Water Engn Arid & Semiarid Are, Minist Educ, Yangling, Shaanxi, Peoples R China.
来源期刊	PEERJ
ISSN	2167-8359
出版年	2020
卷号	8
英文摘要	The accurate and timely monitoring of the soil salt content (SSC) at different depths is the prerequisite for the solution to salinization in the arid and semiarid areas. Sentinel-2 has demonstrated significant superiority in SSC inversion for its higher temporal, spatial and spectral resolution, but previous research on SSC inversion with Sentinel-2 mainly focused on the unvegetated surface soil. Based on Sentinel-2 data, this study aimed to build four machine learning models at five depths (0 similar to 20 cm, 20 similar to 40 cm, 40 similar to 60 cm, 0 similar to 40 cm, and 0 similar to 60 cm) in the vegetated area, and evaluate the sensitivity of Sentinel-2 to SSC at different depths and the inversion capability of the models. Firstly, 117 soil samples were collected from Jiefangzha Irrigation Area (JIA) in Hetao Irrigation District (HID), Inner Mongolia, China during August, 2019. Then a set of independent variables (IVs, including 12 bands and 32 spectral indices) were obtained based on the Sentinel-2 data (released by the European Space Agency), and the full subset selection was used to select the optimal combination of Ws at five depths. Finally, four machine learning algorithms, back propagation neural network (BPNN), support vector machine (SVM), extreme learning machine (ELM) and random forest (RF), were used to build inversion models at each depth. The model performance was assessed using adjusted coefficient of determination (R-adj(2)), root mean square error (RMSE) and mean absolute error (MAE). The results indicated that 20 similar to 40 cm was the optimal depth for SSC inversion. All the models at this depth demonstrated a good fitting (R-adj(2 )approximate to 0.6) and a good control of the inversion errors (RMSE < 0.16%, MAE < 0.12%). At the depths of 40 similar to 60 cm and 0 similar to 20 cm the inversion performance showed a slight and a great decrease respectively. The sensitivity of Sentinel-2 to SSC at different depths was as follows: 20 similar to 40 cm > 40 similar to 60 cm > 0 similar to 40 cm > 0 similar to 60 cm > 0 similar to 20 cm. All four machine learning models demonstrated good inversion performance (R-adj(2) > 0.46). RF was the best model with high fitting and inversion accuracy. Its R-adj(2) at five depths were between 0.5 to 0.68. The SSC inversion capabilities of all the four models were as follows: RF model > ELM model > SVM model > BPNN model. This study can provide a reference for soil salinization monitoring in large vegetated area.
英文关键词	Sentinel-2 Soil salt content Different depths Vegetated area Full subset selection Machine learning
类型	Article
语种	英语
开放获取类型	gold, Green Published
收录类别	SCI-E
WOS记录号	WOS:000600832800013
WOS关键词	EXTREME LEARNING-MACHINE ; LANDSAT 8 OLI ; RANDOM FOREST ; SALINITY ; CLASSIFICATION ; SALINIZATION ; MODEL ; MSI
WOS类目	Multidisciplinary Sciences
WOS研究方向	Science & Technology - Other Topics
来源机构	西北农林科技大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/369189
作者单位	[Chen, Yinwen] Northwest A&F Univ, Dept Foreign Languages, Yangling, Shaanxi, Peoples R China; [Qin, Yuanlin; Zhang, Zhitao; Zhang, Junrui; Han, Jia; Liu, Dan] Northwest A&F Univ, Coll Water Resources & Architectural Engn, Yangling, Shaanxi, Peoples R China; [Zhang, Zhitao; Zhang, Junrui; Han, Jia] Northwest A&F Univ, Key Lab Agr Soil & Water Engn Arid & Semiarid Are, Minist Educ, Yangling, Shaanxi, Peoples R China
推荐引用方式 GB/T 7714	Chen, Yinwen,Qin, Yuanlin,Zhang, Zhitao,et al. Estimating salt content of vegetated soil at different depths with Sentinel-2 data[J]. 西北农林科技大学,2020,8.
APA	Chen, Yinwen,Qin, Yuanlin,Zhang, Zhitao,Zhang, Junrui,Han, Jia,&Liu, Dan.(2020).Estimating salt content of vegetated soil at different depths with Sentinel-2 data.PEERJ,8.
MLA	Chen, Yinwen,et al."Estimating salt content of vegetated soil at different depths with Sentinel-2 data".PEERJ 8(2020).