Abstract
This study explores the feasibility of analyzing soil organic carbon (SOC) in carbonate-rich soils using visible near-infrared spectroscopy (VIS-NIR). Employing a combination of datasets, feature groups, variable selection methods, and regression models, 22 modeling pipelines were developed. Spectral data and spectral data combined with carbonate contents were used as datasets, while raw reflectance, first-derivative (FD) reflectance, and second-derivative (SD) reflectance constituted the feature groups. The variable selection methods included Spearman correlation, Variable Importance in Projection (VIP), and Random Frog (Rfrog), while Partial Least Squares Regression (PLSR), Random Forest Regression (RFR), and Support Vector Regression (SVR) were the regression models. The obtained results indicated that the FD preprocessing method combined with RF, results in the model that is sufficiently robust and stable to be applied to soils rich in calcium carbonate.