Your browser doesn't support javascript.
loading
SoilGrids250m: Global gridded soil information based on machine learning.
Hengl, Tomislav; Mendes de Jesus, Jorge; Heuvelink, Gerard B M; Ruiperez Gonzalez, Maria; Kilibarda, Milan; Blagotic, Aleksandar; Shangguan, Wei; Wright, Marvin N; Geng, Xiaoyuan; Bauer-Marschallinger, Bernhard; Guevara, Mario Antonio; Vargas, Rodrigo; MacMillan, Robert A; Batjes, Niels H; Leenaars, Johan G B; Ribeiro, Eloi; Wheeler, Ichsani; Mantel, Stephan; Kempen, Bas.
Affiliation
  • Hengl T; ISRIC - World Soil Information, Wageningen, the Netherlands.
  • Mendes de Jesus J; ISRIC - World Soil Information, Wageningen, the Netherlands.
  • Heuvelink GB; ISRIC - World Soil Information, Wageningen, the Netherlands.
  • Ruiperez Gonzalez M; ISRIC - World Soil Information, Wageningen, the Netherlands.
  • Kilibarda M; Faculty of Civil Engineering, University of Belgrade, Belgrade, Serbia.
  • Blagotic A; GILab Ltd, Belgrade, Serbia.
  • Shangguan W; School of Atmospheric Sciences, Sun Yat-sen University, Guangzhou, China.
  • Wright MN; Institut für Medizinische Biometrie und Statistik, Lübeck, Germany.
  • Geng X; Agriculture and Agri-Food Canada, Ottawa (Ontario), Canada.
  • Bauer-Marschallinger B; Department of Geodesy and Geoinformation, Vienna University of Technology, Vienna, Austria.
  • Guevara MA; University of Delaware, Newark (DE), United States of America.
  • Vargas R; University of Delaware, Newark (DE), United States of America.
  • MacMillan RA; LandMapper Environmental Solutions Inc., Edmonton (Alberta), Canada.
  • Batjes NH; ISRIC - World Soil Information, Wageningen, the Netherlands.
  • Leenaars JG; ISRIC - World Soil Information, Wageningen, the Netherlands.
  • Ribeiro E; ISRIC - World Soil Information, Wageningen, the Netherlands.
  • Wheeler I; Envirometrix Inc., Wageningen, the Netherlands.
  • Mantel S; ISRIC - World Soil Information, Wageningen, the Netherlands.
  • Kempen B; ISRIC - World Soil Information, Wageningen, the Netherlands.
PLoS One ; 12(2): e0169748, 2017.
Article in En | MEDLINE | ID: mdl-28207752
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 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.
Subject(s)

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Soil / Environmental Monitoring / Geographic Information Systems / Machine Learning / Models, Theoretical Type of study: Prognostic_studies Limits: Humans Language: En Journal: PLoS One Journal subject: CIENCIA / MEDICINA Year: 2017 Document type: Article Affiliation country: Países Bajos Publication country: EEUU / ESTADOS UNIDOS / ESTADOS UNIDOS DA AMERICA / EUA / UNITED STATES / UNITED STATES OF AMERICA / US / USA

Full text: 1 Collection: 01-internacional Database: MEDLINE Main subject: Soil / Environmental Monitoring / Geographic Information Systems / Machine Learning / Models, Theoretical Type of study: Prognostic_studies Limits: Humans Language: En Journal: PLoS One Journal subject: CIENCIA / MEDICINA Year: 2017 Document type: Article Affiliation country: Países Bajos Publication country: EEUU / ESTADOS UNIDOS / ESTADOS UNIDOS DA AMERICA / EUA / UNITED STATES / UNITED STATES OF AMERICA / US / USA