Volumetric Water Content at 10kPa suction in 10-3 cm3cm-3 (0.1 v% or 1 mm/m) at 6 standard depths. Predictions were derived using a digital soil mapping approach based on Quantile Random Forest, drawing on a global compilation of soil profile data and environmental layers. This map is the result of resampling the mean SoilGrids 250 m predictions (Turek et...

Nutrient clusters based on fuzzy k-means of the soil fine earth fraction and spatially predicted at 250 m spatial resolution across sub-Saharan Africa using Machine Learning (ensemble between random forest and gradient boosting) using soil data from the Africa Soil Profiles database (AfSP) compiled by AfSIS and recent soil data newly collected by AfSIS in...

Volumetric Water Content at 33kPa suction in 10-3 cm3cm-3 (0.1 v% or 1 mm/m) at 6 standard depths. Predictions were derived using a digital soil mapping approach based on Quantile Random Forest, drawing on a global compilation of soil profile data and environmental layers.

Volumetric Water Content at 10kPa suction in 10-3 cm3cm-3 (0.1 v% or 1 mm/m) at 6 standard depths. Predictions were derived using a digital soil mapping approach based on Quantile Random Forest, drawing on a global compilation of soil profile data and environmental layers.

Volumetric Water Content at 33kPa suction in 10-3 cm3cm-3 (0.1 v% or 1 mm/m) at 6 standard depths. Predictions were derived using a digital soil mapping approach based on Quantile Random Forest, drawing on a global compilation of soil profile data and environmental layers. This map is the result of resampling the mean SoilGrids 250 m predictions (Turek et...

Volumetric Water Content at 1500kPa suction in 10-3 cm3cm-3 (0.1 v% or 1 mm/m) at 6 standard depths. Predictions were derived using a digital soil mapping approach based on Quantile Random Forest, drawing on a global compilation of soil profile data and environmental layers.

Volumetric Water Content at 1500kPa suction in 10-3 cm3cm-3 (0.1 v% or 1 mm/m) at 6 standard depths. Predictions were derived using a digital soil mapping approach based on Quantile Random Forest, drawing on a global compilation of soil profile data and environmental layers. This map is the result of resampling the mean SoilGrids 250 m predictions (Turek...

Volumetric Water Content at 1500kPa suction in 10-3 cm3cm-3 (0.1 v% or 1 mm/m) at 6 standard depths. Predictions were derived using a digital soil mapping approach based on Quantile Random Forest, drawing on a global compilation of soil profile data and environmental layers. This map is the result of resampling the mean SoilGrids 250 m predictions (Turek...

Volumetric Water Content at 10 kPa suction in 10-3 cm3cm-3 (0.1 v% or 1 mm/m) at 6 standard depths. Predictions were derived using a digital soil mapping approach based on Quantile Random Forest, drawing on a global compilation of soil profile data and environmental layers. This map is the result of resampling the mean SoilGrids 250 m predictions (Turek...

Silt content (2-50/63 micro meter) mass fraction in ‰ at 6 standard depths. Predictions were derived using a digital soil mapping approach based on Quantile Random Forest, drawing on a global compilation of soil profile data and environmental layers. This map is the result of resampling the mean SoilGrids 250 m predictions (Poggio et al. 2021) for each...

Extractable Zinc (Zn) content of the soil fine earth fraction in mg/100kg (pp100m) as measured according to the soil analytical procedure of Mehlich 3 and spatially predicted for 0-30 cm depth interval at 250 m spatial resolution across sub-Saharan Africa using Machine Learning (ensemble between random forest and gradient boosting) using soil data from...

Total plant-available water holding capacity (mm) of the soil whole earth fraction (including coarse fragments), summed over the Effective Root Zone Depth for Maize, mapped at 1km resolution

Probability of occurrence of R horizon predicted using the global compilation of soil ground observations. Accuracy assessement of the maps is availble in Hengl et at. (2017) DOI: 10.1371/journal.pone.0169748. Data provided as GeoTIFFs with internal compression (co='COMPRESS=DEFLATE'). Measurement units: probability.

Textural class (USDA) of the soil fine earth fraction, aggregated over rootable depth and the top 30 cm, mapped at 1km resolution

Sand content (50-2000 micro meter) mass fraction in % at 7 standard depths predicted using the global compilation of soil ground observations. Accuracy assessement of the maps is availble in Hengl et at. (2017) DOI: 10.1371/journal.pone.0169748. Data provided as GeoTIFFs with internal compression (co='COMPRESS=DEFLATE'). Measurement units: w%.

Total nitrogen in cg/kg at 6 standard depths. Predictions were derived using a digital soil mapping approach based on Quantile Random Forest, drawing on a global compilation of soil profile data and environmental layers. This map is the result of resampling the mean SoilGrids 250 m predictions (Poggio et al. 2021) for each 5000 m cell.

Bulk density (fine earth) in kg / cubic-meter at 7 standard depths predicted using the global compilation of soil ground observations. Accuracy assessement of the maps is availble in Hengl et at. (2017) DOI: 10.1371/journal.pone.0169748. Data provided as GeoTIFFs with internal compression (co='COMPRESS=DEFLATE'). Measurement units: kg / m3.

Volumetric moisture content (v%) of the soil fine earth fraction at permanent wilting point (at h=15,000 cm or pF 4.2), aggregated over rootable depth and the top 30 cm, mapped at 1km resolution

Sand content (50/63-2000 micro meter) mass fraction in ‰ at 6 standard depths. Predictions were derived using a digital soil mapping approach based on Quantile Random Forest, drawing on a global compilation of soil profile data and environmental layers. This map is the result of resampling the mean SoilGrids 250 m predictions (Poggio et al. 2021) for each...

Extractable Calcium (Ca) content of the soil fine earth fraction in mg/kg (ppm) as measured according to the soil analytical procedure of Mehlich 3 and spatially predicted for 0-30 cm depth interval at 250 m spatial resolution across sub-Saharan Africa using Machine Learning (ensemble between random forest and gradient boosting) using soil data from the...