Full name:
iSDAsoil
Version:
0.13
Organization or Author:
Abstract:
iSDAsoil is a soil resource created by iSDA, containing soil property predictions at 30m resolution for the entire African continent.
Maps for over 20 different soil properties have been created at three different depth ranges (0-20, 20-50 and 0-200 cm). Soil property predictions were made using machine learning coupled with remote sensing data and a training set of over 100,000 analyzed soil samples. Included in the original resource there are images of predicted soil properties, model error and satellite covariates used in the mapping process.
To explore the iSDAsoil data, it is recommended to visit the iSDAsoil homepage.
Further information can be found in the FAQ section, and technical information documentation
Maps for over 20 different soil properties have been created at three different depth ranges (0-20, 20-50 and 0-200 cm). Soil property predictions were made using machine learning coupled with remote sensing data and a training set of over 100,000 analyzed soil samples. Included in the original resource there are images of predicted soil properties, model error and satellite covariates used in the mapping process.
To explore the iSDAsoil data, it is recommended to visit the iSDAsoil homepage.
Further information can be found in the FAQ section, and technical information documentation
Service location:
Geographical Coverage:
Continental - Africa
GIS Data Type:
Raster
Spatial resolution:
30 m (30 x 30 m pixel)
Publication date:
2020-??-??
Reference period-start:
2001-??-??
Reference period-stop
2017-??-??
License:
Key Soil Properties:
Aluminium, Zinc, Phosphorus, Potassium, Nitrogen, Sulfur, Clay, Iron, Calcium, Magnesium, silt, sand, Cation Exchange Capacity, Carbon Total, Organic Carbon Content, Bulk Density, Coarse Fragments, pH, USDA Texture, Rock Horizon
Soil deph coverage (cm):
Up to 200 cm
Soil Functions:
-
Soil Threats:
-
Citation:
Hengl, T., Miller, M.A.E., Križan, J. et al. African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning. Sci Rep 11, 6130 (2021). https://doi.org/10.1038/s41598-021-85639-y
Soil parameters overview
Please find prediction error layers for each dataset here
| Soil Parameter name | Unit of measurement | Description | Global min value | Global max value |
|---|---|---|---|---|
| Al.mehlich3 | ppm | soil extractable Aluminium (Al) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 1,800 |
| zn.mehlich3 | ppm | soil extractable Zinc (Zn) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 125 |
| p.mehlich3 | ppm | iSDAsoil dataset soil extractable Phosphorus (P) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 125 |
| k_mehlich3 | ppm | soil extractable Potassium (K) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 1,200 |
| n_tot_mehlich3 | g/kg | soil total organic Nitrogen (N) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals | - | 10 |
| s_mehlich3 | ppm | soil extractable Sulphur (S) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals | - | 125 |
| clay_tot_psa | % | soil clay content (USDA system) in % predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals | - | 70 |
| fe_mehlich3 | ppm | soil extractable Iron (Fe) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 1,200 |
| ca_mehlich3 | ppm | soil extractable Calcium log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 12,000 |
| mg_mehlich3 | ppm | soil extractable Magnesium (Mg) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 1,200 |
| silt_tot_psa | % | soil silt content in % predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 70 |
| sand_tot_psa | % | soil sand content in % predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 100 |
| ecec.f | cmolc/kg | soil effective Cation Exchange Capacity (eCEC) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 130 |
| c_tot_mehlich3 | g/kg | soil total carbon in permilles (g/kg) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 40 |
| oc_mehlich3 | g/kg | soil organic carbon (C) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 40 |
| db_od | kg/m3 x 10 | soil fine-earth bulk density in kg/m3 x 10 predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | 0.8 | 1.85 |
| wpg2_mehlich3 | % | soil stone content / coarse fragments log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 80 |
| ph_h2o | pH x 10 | soil pH (1:1 Soil-Water Suspension) predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. | - | 10.50 |
| sol_texture.class_m_30m_0..20cm_2001..2017_v0.13_wgs84 | - | Textural Class for 0-20 cm depth interval, expressed as 1 = Clay, 2 = Silty Clay, 3 = Sandy Clay, 4 = Clay Loam, 5 = Silty Clay Loam, 6 = Sandy Clay Loam, 7 = Loam, 8 = Silty Loam, 9 = Sandy Loam, 10 = Silt, 11 = Loamy Sand, 12 = Sand | - | - |
| sol_texture.class_m_30m_20..50cm_2001..2017_v0.13_wgs84 | - | Textural Class for 20-50 cm depth interval, expressed as 1 = Clay, 2 = Silty Clay, 3 = Sandy Clay, 4 = Clay Loam, 5 = Silty Clay Loam, 6 = Sandy Clay Loam, 7 = Loam, 8 = Silty Loam, 9 = Sandy Loam, 10 = Silt, 11 = Loamy Sand, 12 = Sand | - | - |
| sol_bdr_m_30m_0..200cm_2001..2017_v0.13_wgs84 | cm | Depth to bedrock, predicted mean at 0-200 cm depth | - | - |