Integrating fractional-order derivatives of soil and leaf hyperspectral reflectance for improved estimation of mangrove soil organic carbon

• Published in: Geoderma Vol. 458; p. 117324
• Main Authors: Luo, Yibo, Li, Chunlin, Huang, Jinhong, Dong, Chengcheng, Wang, Junjie
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.06.2025; Elsevier
• Subjects: blue carbon; carbon sequestration; China; clay fraction; Fractional-order derivative; Hyperspectral reflectance; iron; landscapes; Machine learning; Mangrove ecosystem; mangrove soils; prediction; redox potential; reflectance; salinity; Soil organic carbon; topography; vegetation cover; China; Hyperspectral reflectance; Mangrove ecosystem; Soil organic carbon; Fractional-order derivative; Machine learning

•363 modeling strategies were developed for mangrove SOC estimation.•Integrating soil and leaf FOD reflectance improved mangrove SOC estimation.•CatBoost outperformed XGBoost and RF for SOC prediction with FOD features.•CatBoost had good applicability for SOC estimation across regions and communitie...