Modeling of total and active organic carbon dynamics in agricultural soil using digital soil mapping: a case study from Central Nova Scotia

Monitoring the changes in soil organic carbon (SOC) pools is critical for sustainable and agricultural management. This case study models total active dynamics (2015/2016 to 2019/2020) using digital mapping (DSM) techniques. Model predictors include topographic variables generated from light detection ranging data; vegetation indices derived Landsat satellite images; crop inventory information Agriculture Agri-Food Canada predict (TOC) permanganate oxidizable (POXc) at 0–15 cm depth increment a 37 km 2 area Truro, Nova Scotia. Quantile Regression Forest stochastic Gradient Boosting were utilized prediction. Although both performed equally well predicting TOC POXc, accuracy of predictions (e.g., concordance correlation coefficient (CCC) = 0.67) was better than POXc CCC 0.53). The dominant predictors, while across relatively homogeneous terrain had little influence. During period, predicted 98% area, with mean absolute loss 5.77 (±11.48) mg/kg/year, on 27% 0.15 (±0.09) g/kg/year. While annual fields observed highest decline pasture–grassland–forage low. reinforced effectiveness DSM modeling multiple SOC farm landscape scales.