Estimating and predicting the spatial distribution of soil organic carbon (SOC) by Remote Sensing methods

Soil organic carbon is an important indicator for assessing soil health and stability on different type of land use. Accurate prediction of the spatial distribution of soil organic carbon is an important basis for mitigating global warming, ensuring regional food security and maintaining the sustainable development of the territory. The comparison shows the different methods that can be used to accurately predict the spatial distribution of SOC. Also shown are key environmental variables (terrain attributes) and the Spectral Indices that have most significant influence on SOC (feature importance score). Have made comparison of assessment of model performance accuracy (MAE, MSE, RMSE, R2).