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

Abstract

Abstract. Country-specific soil organic carbon (SOC) estimates are the baseline for the Global SOC Map of the Global Soil Partnership (GSOCmap-GSP). This endeavor is key to explaining the uncertainty of global SOC estimates but 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 (SVMs), random forest (RF), kernel-weighted nearest neighbors (KK), partial least squares regression (PL), and regression kriging based on stepwise multiple linear models (RK). Country-specific training data and SOC predictors (5 × 5 km pixel resolution) were obtained from ISRIC -World Soil Information. 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 datasets and models, and were able to explain SOC variability in a range between ∼ 1 and ∼ 60 %, with no universal predictive algorithm among countries. A regional (n = 11 268 SOC estimates) ensemble of these five algorithms was able to explain ∼ 39 % of SOC variability from repeated 5-fold cross-validation. We report a combined SOC stock of 77.8 ± 43.6 Pg (uncertainty represented by the full conditional response of independent model residuals) across Latin America. SOC stocks were higher in tropical forests (30 ± 16.5 Pg) and croplands (13 ± 8.1 Pg). Country-specific and regional ensembles revealed spatial discrepancies across geopolitical borders, higher elevations, and coastal plains, but provided similar regional stocks (77.8 ± 42.2 and 76.8 ± 45.1 Pg, respectively). These results are conservative compared to global estimates (e.g., SoilGrids250m 185.8 Pg, the Harmonized World Soil Database 138.4 Pg, or the GSOCmap-GSP 99.7 Pg). 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 expert opinion is needed to set boundary prediction limits to avoid unrealistically high modeling estimates. For maximizing explained variance while minimizing prediction bias, the selection of predictive algorithms for SOC mapping should consider density of available data and variability of country-specific environmental gradients. This study highlights the large degree of spatial uncertainty in SOC estimates across Latin America. We provide a framework for improving country-specific mapping efforts and reducing current discrepancy of global, regional, and country-specific SOC estimates.

Soil Organic Carbon Across Mexico and the Conterminous United States (1991–2010)

“…Our predicted SOC stock is lower when compared to values obtained from global estimates such as the re‐gridded HWSD (Wieder et al ) or the SoilGrids250m system (Hengl et al, ), where this value increases to ~71 and ~92 Pg of SOC, respectively. High discrepancy of these two global products has been reported earlier at global‐ (Tifafi et al, ), country‐, or region‐specific scales (Guevara et al, , Vitharana et al, ). Moreover, our results showed discrepancies comparing country‐specific studies reporting SOC stocks in CONUS (29.3 Pg of SOC; Bliss et al, ) and Mexico (9.15 Pg; Cruz‐Gaistardo & Paz‐Pellat, , Paz Pellat et al, ), as we report ~39 Pg of SOC for CONUS and ~7 Pg of SOC for Mexico in the first 30 cm of soil.…”

“…Moreover, our results showed discrepancies comparing country‐specific studies reporting SOC stocks in CONUS (29.3 Pg of SOC; Bliss et al, ) and Mexico (9.15 Pg; Cruz‐Gaistardo & Paz‐Pellat, , Paz Pellat et al, ), as we report ~39 Pg of SOC for CONUS and ~7 Pg of SOC for Mexico in the first 30 cm of soil. Our results highlight the need to provide country‐to‐region specific estimates using the best available datasets, to improve global SOC estimates by developing analytical frameworks for optimizing multiple SOC modeling efforts and sampling strategies (Guevara et al, ).…”

“…Optimizing future SOC sampling strategies while reducing modeling variance and increasing model agreement against model independent datasets collected under different circumstances (e.g., logistics, design, main purpose, and SOC estimation methods) are large challenges for enabling SOC carbon mapping and monitoring systems. New and better SOC parameters are required for reducing the current discrepancy between multiple sources of SOC data (Guevara et al, ; Tifafi et al, ) and enabling SOC monitoring systems (Viscarra‐Rossel et al, ). The lack of accurate SOC spatial information and the combination of multiple SOC data sources could result in large variance estimates across the two countries (e.g., red areas of Figure ).…”

“…Large discrepancies have been reported among global (Tifafi et al, ) or country‐specific SOC estimates (Guevara et al, ). Consequently, reporting uncertainty and bias of SOC estimates will allow better parameterization of land surface models, improved local to regional monitoring baselines, and informed policy and management decisions regarding SOC stocks (Viscarra‐Rossel et al, ).…”

Standardised soil profile data to support global mapping and modelling (WoSIS snapshot 2019)

“…Quality-assessed data provided through WoSIS can be (and have been) used for various purposes. For example, as point data for making soil property maps at various spatialscale levels, using digital soil mapping techniques (Arrouays et al, 2017;Guevara et al, 2018;Hengl et al, 2017a, b;Moulatlet et al, 2017). Such property maps, for example, can be used to study global effects of soil and climate on leaf photosynthetic traits and rates (Maire et al, 2015), generate maps of root zone plant-available water capacity (Leenaars et al, 2018) in support of yield gap analyses (van Ittersum et al, 2013), assess impacts of long-term human land use on world soil carbon stocks (Sanderman et al, 2017), or the effects of tillage practices on soil gaseous emissions (Lutz et al, 2019).…”