SoilGrids overview

SoilGrids is an automated system for global soil mapping based on the machine learning and global soil profile data collections. All predictions are based on fitting global spatial prediction models (per variable). For more info see the SoilGrids home page.

What to find on this repository:

• R scripts documenting import and merging of soil profile data,
• R/OSGeo scripts documenting preparation of soil covariates using the Equi7 grid tiling system,
• R scripts documenting model fitting and prediction,
• Examples of predictions, outputs and visualizations,

Citation:

• Hengl, T., Mendes de Jesus, J., Heuvelink, G. B.M., Ruiperez Gonzalez, M., Kilibarda, M. et al. (2017) SoilGrids250m: global gridded soil information based on Machine Learning. PLOS One, accepted.
• Shangguan, W., Hengl, T., de Jesus, J. M., Yuan, H. and Dai, Y. (2016), Mapping the global depth to bedrock for land surface modeling. J. Adv. Model. Earth Syst. accepted, doi:10.1002/2016MS000686
• Hengl T, de Jesus JM, MacMillan RA, Batjes NH, Heuvelink GBM, et al. (2014) SoilGrids1km — Global Soil Information Based on Automated Mapping. PLoS ONE 9(8): e105992. doi:10.1371/journal.pone.0105992 ISRIC – World Soil Information, 2013.
• SoilGrids: an automated system for global soil mapping. Available for download at http://soilgrids.org