Reply on RC3

Abstract

The manuscript is well written and generally clear, with an appropriate structure and the information provided in tables and figures is useful and necessary, although I have some specific comments for the presentation of some figures. The length of the paper is appropriate, as the presentation of the results is synthetic, and the discussion gives a concise explanation of the observed results supported by other findings in the SOC literature. This research paper investigated the key variables for predicting soil organic carbon (SOC) stocks in the litter layer, mineral soil, and total SOC of forest soils in Sweden, and maps its spatial distribution using random forest models. The study compares the accuracy of global models (calibrated for the whole study area, Sweden) and local models for north, central and southern Sweden. The calibration data originated from the Swedish National Forest and as predictor variables they compared three different sets: 1) only site variables observed at the sampling plots, 2) remote sensing variables, and 3) all variables. My main comment may be more a suggestion for the follow-up study. Mapping some of the site variables that were more decisive for SOC prediction (soil moisture class, vegetation type, soil type and soil texture) and including them as covariates for mapping may improve the model accuracy for mapping. However, as these variables will be themselves estimated with statistical models, there may be an increase in the uncertainty due to error propagation. Hence, the uncertainty of the map for a model including all variables may be a conservative estimate. Also, in that future scenario, consider that if you calibrate the model with the data observed at the plots but map it with the gridded estimates of the site variables, the accuracy may also overestimated. If you calibrate the model with the gridded predictions for soil C2 SOILD