SoilGrids250m: Global gridded soil information based on machine learning

Abstract

This paper describes the technical development and accuracy assessment of the most recent and improved version of the SoilGrids system at 250m resolution (June 2016 update). SoilGrids provides global predictions for standard numeric soil properties (organic carbon, bulk density, Cation Exchange Capacity (CEC), pH, soil texture fractions and coarse fragments) at seven standard depths (0, 5, 15, 30, 60, 100 and 200 cm), in addition to predictions of depth to bedrock and distribution of soil classes based on the World Reference Base (WRB) and USDA classification systems (ca. 280 raster layers in total). Predictions were based on ca. 150,000 soil profiles used for training and a stack of 158 remote sensing-based soil covariates (primarily derived from MODIS land products, SRTM DEM derivatives, climatic images and global landform and lithology maps), which were used to fit an ensemble of machine learning methods—random forest and gradient boosting and/or multinomial logistic regression—as implemented in the packages , , and . The results of 10–fold cross-validation show that the ensemble models explain between 56% (coarse fragments) and 83% (pH) of variation with an overall average of 61%. Improvements in the relative accuracy considering the amount of variation explained, in comparison to the previous version of SoilGrids at 1 km spatial resolution, range from 60 to 230%. Improvements can be attributed to: (1) the use of machine learning instead of linear regression, (2) to considerable investments in preparing finer resolution covariate layers and (3) to insertion of additional soil profiles. Further development of SoilGrids could include refinement of methods to incorporate input uncertainties and derivation of posterior probability distributions (per pixel), and further automation of spatial modeling so that soil maps can be generated for potentially hundreds of soil variables. Another area of future research is the development of methods for multiscale merging of SoilGrids predictions with local and/or national gridded soil products (e.g. up to 50 m spatial resolution) so that increasingly more accurate, complete and consistent global soil information can be produced. SoilGrids are available under the Open Data Base License.

Soil nutrient maps of Sub-Saharan Africa: assessment of soil nutrient content at 250 m spatial resolution using machine learning

“…As spatial covariates, a large stack of GIS layers as proxies for soil forming processes (climate, landform, lithology and vegetation) was used: Remote sensing data had been previously downloaded and prepared via ISRIC's massive storage server for the purpose of the SoilGrids project (Hengl et al 2017). The majority of covariates cover the time period 2000-2015, i.e.…”

“…Model fitting and prediction were undertaken using an ensemble of two Machine Learning algorithms (MLA) (Hengl et al 2017): ranger (random forest) (Wright and Ziegler 2016) and xgboost (Gradient Boosting Tree) (Chen and Guestrin 2016), as implemented in the R environment for statistical computing. Both random forest and gradient boosting have already proven to be efficient in predicting soil chemical and physical soil properties at the continental and global scale (Hengl et al 2017).…”

“…The Africa Soil Information Services project has recently developed a gridded Soil Information System of Africa at 250 m resolution showing the spatial distribution of primary soil properties of relatively stable nature, such as depth to bedrock, soil particle size fractions (texture), pH, contents of coarse fragments, organic carbon and exchangeable cations such as Ca, Mg, Na, K and Al and the associated cation exchange capacity (Hengl et al , 2017. These maps were derived from a compilation of soil profile data collected from current and previous soil surveys.…”

No Silver Bullet for Digital Soil Mapping: Country-specific Soil Organic Carbon Estimates across Latin America

“…Data mining techniques have been successfully used to model and predict the spatial variability of soil properties (Rossel and Behrens, 2010;Hengl et al, 2017;Shangguan et al, 2017) and generate country-specific SOC maps (Viscarra Rossel et al, 2014;Adhikari et al, 2014). The combination of regression modeling approaches with geostatistics of model residuals (i.e., regression Kriging) is a combined strategy that 30 has been widely used to map SOC (Hengl et al, 2004;Mishra et al, 2009;Marchetti et al, 2012;Kumar et al, 2012;Peng et al, 2013;Adhikari et al, 2014;Yigini and Panagos, 2016;Nussbaum et al, 2014;Mondal et al, 2017).…”

“…carbon models (Martin et al, 2011;Hashimoto et al, 2017;Hengl et al, 2017) including applications for SOC mapping (Grimm et al, 2008;Sreenivas et al, 2016;Yang et al, 2016;Hengl et al, 2017;Delgado-Baquerizo et al, 2017;Ließ et al, 2016;Viscarra Rossel et al, 2014).Machine learning methods do not necessarily allow to extract information about the main effects of prediction factors in the response variable (e.g., SOC); consequently, a selection strategy is always useful to increase the interpretability of machine learning algorithms. With this diversity of approaches one constant question is if there is a 5 method that systematically improve the prediction capacity of the others aiming to predict SOC across large geographic areas (e.g., Latin America).…”