Knowledge Resource Center for Ecological Environment in Arid Area
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). |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。