Skip to contents

SoilGrids is a project combining global observation data with machine learning to map the spatial distribution of soil properties across the globe. It is produced at a spatial resolution of 250 meters and each parameters is mapped at different depths. In order to be able to assess prediction uncertainty, besides the mean and median prediction, the 0.05 and 0.95 percentile predictions are available. The following parameters are available:

bdod

Bulk density of the fine earth fraction (kg/dm3)

cec

Cation Exchange Capacity of the soil (cmol(c)/kg)

cfvo

Volumetric fraction of coarse fragments > 2 mm (cm3/100cm3 (volPerc))

clay

Proportion of clay particles < 0.002 mm in the fine earth fraction (g/100g)

nitrogen

Total nitrogen (g/kg)

phh2o

Soil pH (pH)

sand

Proportion of sand particles > 0.05 mm in the fine earth fraction (g/100g)

silt

Proportion of silt particles >= 0.002 mm and <= 0.05 mm in the fine earth fraction (g/100g)

soc

Soil organic carbon content in the fine earth fraction (g/kg)

ocd

Organic carbon density (kg/m3)

ocs

Organic carbon stocks (kg/m²)

Format

A global tiled raster resource available for all land areas.

Details

Users can specify the following arguments:

layer

The soil parameter as a single character

depth

The requested depth as a single character

stat

The predicted statistic as a single character

Except for ocs, which is only available for a depth of "0-30cm", all other parameters are available at the following depths:

  • "0-5cm"

  • "5-15cm"

  • "15-30cm"

  • "30-60cm"

  • "60-100cm"

  • "100-200cm"

Each parameter and depth is available for the following statistics:

  • "Q0.05"

  • "Q0.50"

  • "mean"

  • "Q0.95"

References

Hengl T, Mendes de Jesus J, Heuvelink GBM, Ruiperez Gonzalez M, Kilibarda M, et al. (2017) SoilGrids250m: Global gridded soil information based on machine learning. PLOS ONE 12(2): e0169748. doi:10.1371/journal.pone.0169748