.png){kind=icon}
.png){kind=icon}
Return
Mapping soil particle fractions by training digital soil mapping models with surrogate measurements obtained from laboratory and satellite Vis-NIR spectral data
.png){kind=icon}
OA
AI
S
M
P
C
DOI：10.1016/j.geoderma.2026.117981.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Towards improved soil particle mapping using surrogate data. • Best clay predictions are based on S2 data restricted to bare soil pixels. • Best sand predictions are based on environmental covariates and S2 data covering all pixels. • Usefulness of low density of data with high accuracy to slightly improve DSM. • Usefulness of high data density even with moderate accuracy to substantially improve DSM.
Keywords:
Remote sensing
Sentinel-2
Laboratory Vis-NIR spectroscopy
Random forest
Soil texture
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.6
Papers:
9.3K
Citations:
4.5W
Organization
Cited Papers