No silver bullet for digital soil mapping: country-specific soil organic carbon estimates across Latin America

Country-specific soil organic carbon (SOC) maps are the baseline for the Global SOC Map of the Global Soil Partnership (GSOCmap-GSP). This endeavor requires harmonizing heterogeneous datasets and building country-specific capacities for digital soil mapping (DSM). We identified country-specific predictors for SOC and tested the performance of five predictive algorithms for mapping SOC across Latin America. The algorithms included: support vector machines, random forest, kernel weighted nearest neighbors, partial least squares regression, and regression-Kriging based on stepwise multiple linear models. Country-specific training data and SOC predictors (5 × 5 km pixel resolution) were obtained from ISRIC-World-Soil-Information-System. In general, temperature, soil type, vegetation indices and topographic constraints were the best predictors for SOC, but country-specific predictors and their respective weights varied across Latin America. We compared a large diversity of country-specific data scenarios and were able to explain ~ 53 % of SOC variability (range < 1 % and 80 %) with no universal predictive algorithm among countries. Overall, countries with large area (i.e., Brazil, Bolivia, Mexico, Peru) and large spatial SOC heterogeneity had lower SOC stocks per unit area and larger uncertainty in their predictions. We highlight that setting unreliable (excessive or low) model prediction limits can have important effects (under or overestimating) for predicting SOC; thus expert opinion is needed to set boundary prediction limits. Selection of predictive algorithms should consider density and variability of country-specific available SOC data and country-specific environmental gradients to maximize explained variance while minimizing prediction bias. To progress with country-specific SOC mapping, we call for improvements on quality and quantity of country-specific SOC measurements and associated predictors. This study highlights the large degree of spatial heterogeneity of SOC across Latin America, and provides a reproducible framework that could be used for building DSM capacity to improve country-specific SOC estimates.