SoilGrids250m: Global gridded soil information based on machine learning
By Tomislav Hengl, Jorge Mendes de Jesus, Gerard B. M. Heuvelink, Maria Ruiperez González, M. Kilibarda, Aleksandar Blagotić, Shangguan Wei, Marvin N. Wright, X. Geng, B. Bauer-Marschallinger and 9 more. PLoS ONE, 2017
3,747 citations recorded by the source corpus.
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 R packages ranger, xgboost, nnet and caret. 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.
Subfields: Computer Vision and Pattern Recognition, Environmental Engineering, Soil Science
View Paper: https://www.semanticscholar.org/paper/9e27190f2d9b2167d4a66b88696def4585072fd5
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
In Environmental Engineering
- Leonardo Ramirez-Lopez
- Wolfgang Wagner
- R. B. Jackson
- Pete Smith
- Tomislav Hengl
- Jonathan Sanderman
- D. Rasse
- Shree R. S. Dangal
In Soil Science
- R. B. Jackson
- Jean-François Soussana
- Pete Smith
- Tomislav Hengl
- Claire Chenu
- D. Fornara
- N. Chirinda
- Jonathan Sanderman
Citations in the corpus
- Mountains, climate and niche heterogeneity explain global patterns of fern diversity (2021, methodology): “SoilGrids250m: Global gridded soil information based on machine learning.”
- Accurate and Precise Prediction of Soil Properties from a Large Mid-Infrared Spectral Library (2019, background): “[65] indicated that 150 trees are optimal to achieve a stable random forest model, beyond which a trade-off between the computation time and model accuracy offers no additional benefits.”
- Large stocks of peatland carbon and nitrogen are vulnerable to permafrost thaw (2020, positive): “The SoilGrids250m and the national/regional soil maps were combined and harmonized for this study; see SI Appendix for more details.”
- A global map of mangrove forest soil carbon at 30 m spatial resolution (2018, background): “Soil carbon typically varies in highly non-linear ways with depth and across the landscape and as such the ability of standard parametric models to capture this variation is limited (Jardine and Siikamäki 2014, Hengl et al 2017).”
- The Ecology of Soil Carbon: Pools, Vulnerabilities, and Biotic and Abiotic Controls (2017, methodology): “Using machine-learning techniques, Hengl et al. (2017) modeled soil properties for the world at a resolution as fine as 250 m.”
- Origins of global mountain plant biodiversity: Testing the ‘mountain‐geobiodiversity hypothesis’ (2019, methodology): “We de‐ rived a soil index for each grid cell based on the number of soil types from the SoilGrids repository (Hengl et al., 2017) which is based on the World Reference Base for Soils system (IUSS Working Group WRB, 2015).”