干旱区生态环境知识资源中心(Arid): The inversion of arid-coastal cultivated soil salinity using explainable machine learning and Sentinel-2

Arid

DOI	10.1016/j.ecolind.2024.112364
	The inversion of arid-coastal cultivated soil salinity using explainable machine learning and Sentinel-2
	Jia, Pingping; Zhang, Junhua; Liang, Yanning; Zhang, Sheng; Jia, Keli; Zhao, Xiaoning
通讯作者	Zhang, JH
来源期刊	ECOLOGICAL INDICATORS
ISSN	1470-160X
EISSN	1872-7034
出版年	2024
卷号	166
英文摘要	The escalating salinization of cultivated soil poses a significant threat to the ecological environment. It is imperative to establish a monitoring system and mitigate the spread of salinization in arid and coastal areas through remote sensing, incorporating high-precision cross-regional models for soil salt content inversion. This study focuses on typical saline-alkali soils in arid and coastal regions of China. Using Sentinel 2 data (including 6 bands and 27 spectral indices), along with soil texture, moisture content, temperature, precipitation, and digital elevation model (DEM) data to establish an arid-coastal salinity inversion model. Variable selection methods such as pearson correlation coefficient (PCC), variable importance in projection (VIP), gray relational analysis (GRA), and gradient boosting machine (GBM) were used, while using 9 models including adaptive boosting (Adaboost), extremely randomized trees (ERT), and light gradient boosting machine (LightGBM). The best model was further elucidated using the Shapley additive explanations method. Results indicate that the common sensitive characteristic variables of arid-coastal areas were spectral indices and soil properties in PCC, the spectral variable bands and indices in VIP, and all variables in GRA and GBM. The best inversion model GBM-ERT (R2 R 2 = 0.91, RMSE = 1.06) in arid areas exhibited higher accuracy than the best inversion model GBM-Adaboost (R2 R 2 = 0.77, RMSE = 1.74) in coastal areas. The arid-coastal inversion model PCC-LightGBM demonstrated the best inversion performance (R2 R 2 = 0.64, RMSE = 2.29) and simulation performance in arid (R2 R 2 = 0.67) and coastal areas (R2 R 2 = 0.63). Dead fuel index (DFI) had the most significant impact on model prediction (0.89) and the second ratio index (RI2) contributed the highest relative importance (18 %) to the model. Our analysis indicates that the arid-coastal model of PCC-LightGBM established using common characteristic variables, can effectively monitor large-scale soil salinity.
英文关键词	Arid-coastal area Sustainable land use Soil health Remote sensing Environment variables
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:001284280700001
WOS关键词	VEGETATION INDEXES ; NEURAL-NETWORK ; CONTEXT ; CHINA
WOS类目	Biodiversity Conservation ; Environmental Sciences
WOS研究方向	Biodiversity & Conservation ; Environmental Sciences & Ecology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/403414
推荐引用方式 GB/T 7714	Jia, Pingping,Zhang, Junhua,Liang, Yanning,et al. The inversion of arid-coastal cultivated soil salinity using explainable machine learning and Sentinel-2[J],2024,166.
APA	Jia, Pingping,Zhang, Junhua,Liang, Yanning,Zhang, Sheng,Jia, Keli,&Zhao, Xiaoning.(2024).The inversion of arid-coastal cultivated soil salinity using explainable machine learning and Sentinel-2.ECOLOGICAL INDICATORS,166.
MLA	Jia, Pingping,et al."The inversion of arid-coastal cultivated soil salinity using explainable machine learning and Sentinel-2".ECOLOGICAL INDICATORS 166(2024).