Optimizing environmental covariates for digital mapping of soil organic carbon in Hunan Province, China

Xiaojing Cai, Falin Liu, Zhengui Cai · 2026

Read Optimizing environmental covariates for digital mapping of soil organic carbon in Hunan Province, China by Xiaojing Cai, Falin Liu, Zhengui Cai (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13473560.txt.

Description

Xiaojing Cai and two colleagues mapped in 2026 soil organic carbon across Hunan Province, China, using far fewer variables than usual. Soil organic carbon signals fertility, ecosystem function, and soil health, and land managers need continuous maps of it, yet models often drown in redundant inputs. The team collected and laboratory-tested 477 soil samples, derived terrain and spectral indices from satellite data, and tested support vector machines, neural networks, and random forests.

Variable selection by variance inflation factor and the Boruta method narrowed 40 candidate covariates to just five optimal ones, cutting cost without losing accuracy. With those five, the random forest model performed best, reaching an R-squared of 0.84, a root mean square error of 0.069 percent, and a performance-to-deviation ratio of 3.6 percent. The authors present the lean model as a precise basis for soil management and farm planning in Hunan, and as a template for carbon mapping elsewhere.

Catalog record

CREATORXiaojing Cai, Falin Liu, Zhengui Cai
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE37 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13473560

Browse the full library · About the Tower of Babel