On digital soil assessment with models and the Pedometrics agenda

Finke, Peter

doi:10.1016/j.geoderma.2011.01.001

Cited by 49 publications

(35 citation statements)

References 82 publications

(96 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Large values of EC r represent an accuracy limitation that was evident for RF, PL, and KK. To overcome these types of modeling biases, previous studies have suggested that the theory of ensemble learning applied to soil datasets could increase the accuracy of results (Finke, 2012;Nussbaum et al, 2018). Furthermore, recent studies highlight the applicability of selective ensembles across a large diversity of model algorithms useful for digital soil mapping purposes (Møller et al, 2018).…”

Section: Discussionmentioning

confidence: 99%

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

Guevara

Olmedo

Stell

et al. 2018

SOIL

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

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

Guevara

Olmedo

Stell

et al. 2018

SOIL

View full text Add to dashboard Cite

show abstract

“…In case of models with limited runtime, more advanced calibration methods are available, which are simultaneously changing all model parameters (see also Finke (2012b), p.10 and references therein): III. Methods that sample parameter space and for each run with a parameter vector θ evaluate the value of a cost function C(θ) that describes the misfit between observed and calculated soil properties.…”

Section: Methods For Calibrating and Testing Soil-landscape Modelsmentioning

confidence: 99%

Resolving the integral connection between pedogenesis and landscape evolution

Minasny

Finke

Stockmann

et al. 2015

Earth-Science Reviews

View full text Add to dashboard Cite

“…Apart from the fact that soil boundaries represent transition zones of soil properties (Lagacherie et al, 1996), there are misfits between original paper maps and actual, more accurate, soil-related information, like digital elevation models (DEM) or remote sensing data. In addition, soil map boundaries must often be considered as the result of a subjective -and therefore not reproducible -delineation (Carré et al, 2007a;Möller et al, 2012;Finke, 2012).…”

Section: Introductionmentioning

confidence: 99%

“…The location of legacy soil samples is also often concerned by an unknown positional accuracy which can cause incorrect co-variate assignments (Finke, 2012).…”

Section: Introductionmentioning

confidence: 99%