FAQs

Looking for answers?
Please consult the frequently asked questions below. If you don’t find what you are looking for, you can send us your question.
-
What information on soil properties have you made available?
We’ve created predictions for a number of different chemical, physical and agronomic soil properties. Where we’ve predicted numerical values, we have also included estimates of uncertainty. For categorical data and some other third-party layers, no uncertainty measurements are available.
The below table refers to data available via the iSDAsoil API. For data available via bulk download, visit the iSDAsoil on AWS page.
Property Extraction / Measurement information Unit Available Depths (cm) Geospatial Resolution (m) Theme Uncertainty Available? Model Accuracy (R-square) RMSE Attribution Land Cover (2015 – 2019) N/A % 0 100 Agronomy information No N/A N/A Yes Landcover images courtesy of Copernicus Land Monitoring Service Cropland (2015 – 2019) N/A % 0 100 Agronomy information No N/A N/A Yes Cropland images courtesy of Copernicus Land Monitoring Service Slope Angle N/A degree 0 30 Physical soil properties and landscape No N/A N/A Fertility Capability Classification N/A None 0-50 30 Agronomy information No N/A N/A USDA Texture Class USDA 12 class system None 0-20, 20-50 30 Physical soil properties and landscape No N/A N/A Clay content Various % 0-20, 20-50 30 Physical soil properties and landscape Yes 0.746 9.6 Bulk density, <2mm fraction Various g/cc 0-20, 20-50 30 Physical soil properties and landscape Yes 0.819 126 Aluminium, extractable Mehlich-3 ppm 0-20, 20-50 30 Soil nutrients Yes 0.881* 0.321* Carbon, total Various g/kg 0-20, 20-50 30 Soil properties Yes 0.794* 0.291* Calcium, extractable Mehlich-3 ppm 0-20, 20-50 30 Soil nutrients Yes 0.840* 0.543* Effective Cation Exchange Capacity Mehlich-3 cmol(+)/kg 0-20, 20-50 30 Chemical soil properties Yes 0.754* 0.417* Iron, extractable Mehlich-3 ppm 0-20, 20-50 30 Soil nutrients Yes 0.817* 0.235* Potassium, extractable Mehlich-3 ppm 0-20, 20-50 30 Soil nutrients Yes 0.773* 0.509* Magnesium, extractable Mehlich-3 ppm 0-20, 20-50 30 Soil nutrients Yes 0.815* 0.497* Nitrogen, total Measured by Total combustion g/kg 0-20, 20-50 30 Chemical soil properties Yes 0.732* 0.197* Carbon, organic Various g/kg 0-20, 20-50 30 Chemical soil properties Yes 0.791* 0.369* Phosphorus, extractable Mehlich-3 ppm 0-20, 20-50 30 Soil nutrients Yes 0.486* 0.707* Sulphur, extractable Mehlich-3 ppm 0-20, 20-50 30 Soil nutrients Yes 0.548* 0.384* Zinc, extractable Mehlich-3 ppm 0-20, 20-50 30 Soil nutrients Yes 0.711* 0.375* pH 1:1 Soil-Water Suspension – 0-20, 20-50 30 Chemical soil properties Yes 0.818 0.459 Sand content Various % 0-20, 20-50 30 Physical soil properties and landscape Yes 0.736 13.7 Silt content Various % 0-20, 20-50 30 Physical soil properties and landscape Yes 0.64 8.92 Stone content Various % 0-20, 20-50 30 Physical soil properties and landscape Yes 0.709* 0.803* Depth to Bedrock Estimated from soil profile data cm 0-200 30 Physical soil properties and landscape Yes 0.429 41.3 Land Cover (2015 – 2019) Extraction / Measurement information N/A Unit % Available Depths (cm) 0 Geospatial Resolution (m) 100 Theme Agronomy information Uncertainty Available? No Model Accuracy (R-square) N/A RMSE N/A Attribution Yes Landcover images courtesy of Copernicus Land Monitoring Service Cropland (2015 – 2019) Extraction / Measurement information N/A Unit % Available Depths (cm) 0 Geospatial Resolution (m) 100 Theme Agronomy information Uncertainty Available? No Model Accuracy (R-square) N/A RMSE N/A Attribution Yes Cropland images courtesy of Copernicus Land Monitoring Service Slope Angle Extraction / Measurement information N/A Unit degree Available Depths (cm) 0 Geospatial Resolution (m) 30 Theme Physical soil properties and landscape Uncertainty Available? No Model Accuracy (R-square) N/A RMSE N/A Fertility Capability Classification Extraction / Measurement information N/A Unit None Available Depths (cm) 0-50 Geospatial Resolution (m) 30 Theme Agronomy information Uncertainty Available? No Model Accuracy (R-square) N/A RMSE N/A USDA Texture Class Extraction / Measurement information USDA 12 class system Unit None Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Physical soil properties and landscape Uncertainty Available? No Model Accuracy (R-square) N/A RMSE N/A Clay content Extraction / Measurement information Various Unit % Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Physical soil properties and landscape Uncertainty Available? Yes Model Accuracy (R-square) 0.746 RMSE 9.6 Bulk density, <2mm fraction Extraction / Measurement information Various Unit g/cc Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Physical soil properties and landscape Uncertainty Available? Yes Model Accuracy (R-square) 0.819 RMSE 126 Aluminium, extractable Extraction / Measurement information Mehlich-3 Unit ppm Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Soil nutrients Uncertainty Available? Yes Model Accuracy (R-square) 0.881* RMSE 0.321* Carbon, total Extraction / Measurement information Various Unit g/kg Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Soil properties Uncertainty Available? Yes Model Accuracy (R-square) 0.794* RMSE 0.291* Calcium, extractable Extraction / Measurement information Mehlich-3 Unit ppm Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Soil nutrients Uncertainty Available? Yes Model Accuracy (R-square) 0.840* RMSE 0.543* Effective Cation Exchange Capacity Extraction / Measurement information Mehlich-3 Unit cmol(+)/kg Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Chemical soil properties Uncertainty Available? Yes Model Accuracy (R-square) 0.754* RMSE 0.417* Iron, extractable Extraction / Measurement information Mehlich-3 Unit ppm Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Soil nutrients Uncertainty Available? Yes Model Accuracy (R-square) 0.817* RMSE 0.235* Potassium, extractable Extraction / Measurement information Mehlich-3 Unit ppm Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Soil nutrients Uncertainty Available? Yes Model Accuracy (R-square) 0.773* RMSE 0.509* Magnesium, extractable Extraction / Measurement information Mehlich-3 Unit ppm Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Soil nutrients Uncertainty Available? Yes Model Accuracy (R-square) 0.815* RMSE 0.497* Nitrogen, total Extraction / Measurement information Measured by Total combustion Unit g/kg Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Chemical soil properties Uncertainty Available? Yes Model Accuracy (R-square) 0.732* RMSE 0.197* Carbon, organic Extraction / Measurement information Various Unit g/kg Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Chemical soil properties Uncertainty Available? Yes Model Accuracy (R-square) 0.791* RMSE 0.369* Phosphorus, extractable Extraction / Measurement information Mehlich-3 Unit ppm Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Soil nutrients Uncertainty Available? Yes Model Accuracy (R-square) 0.486* RMSE 0.707* Sulphur, extractable Extraction / Measurement information Mehlich-3 Unit ppm Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Soil nutrients Uncertainty Available? Yes Model Accuracy (R-square) 0.548* RMSE 0.384* Zinc, extractable Extraction / Measurement information Mehlich-3 Unit ppm Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Soil nutrients Uncertainty Available? Yes Model Accuracy (R-square) 0.711* RMSE 0.375* pH Extraction / Measurement information 1:1 Soil-Water Suspension Unit – Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Chemical soil properties Uncertainty Available? Yes Model Accuracy (R-square) 0.818 RMSE 0.459 Sand content Extraction / Measurement information Various Unit % Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Physical soil properties and landscape Uncertainty Available? Yes Model Accuracy (R-square) 0.736 RMSE 13.7 Silt content Extraction / Measurement information Various Unit % Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Physical soil properties and landscape Uncertainty Available? Yes Model Accuracy (R-square) 0.64 RMSE 8.92 Stone content Extraction / Measurement information Various Unit % Available Depths (cm) 0-20, 20-50 Geospatial Resolution (m) 30 Theme Physical soil properties and landscape Uncertainty Available? Yes Model Accuracy (R-square) 0.709* RMSE 0.803* Depth to Bedrock Extraction / Measurement information Estimated from soil profile data Unit cm Available Depths (cm) 0-200 Geospatial Resolution (m) 30 Theme Physical soil properties and landscape Uncertainty Available? Yes Model Accuracy (R-square) 0.429 RMSE 41.3 -
How were these maps made?
A detailed description of our workflow is available on the technical information page.
-
Why is the data free?
A lot of the data that was the basis of iSDAsoil was created by grant-funded projects. We felt that the best thing to do was to make this data easily accessible and readily useable. Even as a profit-seeking company, we pursue a business model around advisory services built upon the foundations of publicly generated data.
-
How can I contribute data to help improve the maps?
We are keen to create maps that are constantly improving. If you’re aware of some legacy soil data or have been involved in data collection, please let us know. We’ll be happy to integrate it and provide acknowledgment.
Contact us to share information about your dataset, and we’ll be in touch.
-
How can I report a problem with the data?
You can get in touch via email at our Contact us page
-
What locations have you predicted soil properties for?
We have covered all areas suitable for agriculture across Africa. For the majority of properties, we have not made predictions for locations classed as deserts or water bodies. You can check the map to see where predictions were made for each layer.
-
What is the fertility capability classification (FCC) layer?
We’ve created a partial implementation of the soil FCC framework, as developed by Sanchez et al. (2013), in order to assess soil quality in the tropics. The idea behind this layer is to inform users about possible constraints that may need to be addressed in order to make soil productive and fertile. As data was not available for all soil constraints, we’ve produced a subset of the total constraints, with minor modifications:
Shallow: Depth to bedrock less than 50cm
Gravel: Stone content more than 10%
Slope: slope angle more than 15°High erosion risk: Textual discontinuity (any of the following):
- USDA Texture class of 0-20cm layer = Sand or Loamy Sand, and USDA Texture class of 20-50cm layer = Sandy clay, Silty Clay or Clay
- USDA Texture class of 0-20cm layer = Sand, Loamy sand, Sandy loam, Loam, Silty loam, Silt, or Sandy clay loam, and USDA Texture class of 20-50cm layer = Clay Loam, Silty clay loam, Sandy Clay, Silty Clay, or Clay
High erosion risk: Shallow depth (any of the following):
- USDA Texture class of 0-20cm layer = Clay Loam, Silty clay loam, Sandy Clay, Silty Clay or Clay, and depth to bedrock less than 50cm
- USDA Texture class of 0-20cm layer = Sand, Loamy sand, Sandy loam, Loam, Silty loam, Silt or Sandy clay loam, and depth to bedrock less than 50cm
- USDA Texture class of 0-20cm layer = Sand or Loamy Sand, and depth to bedrock depth less than 50cm
High erosion risk: Steep slope: slope more than 30°
Sulfidic: pH of 0-20cm or 20-50cm layer less than 3.5
Aluminium toxicity: Organic carbon less than 120g/kg in 0-20 or 20-50cm layer, and pH between 3.5 and 5.5 in 0-20cm or 20-50cm layer
Calcareous: pH more than 7.3 in 0-20 or 20-50cm layer
Low potassium reserves: extractable potassium less than 78ppm, and pH less than 7.5 in 0-20cm or 20-50cm layer
High leaching potential: Cation exchange capacity less than 4cmol/kg in 0-20cm or 20-50cm layer
No constraints: if none of the above are satisfied. Other constraints may be present that we have not mapped. -
How accurate is the data?
The majority of the soil property layers were created using machine learning and are therefore predictions. For each prediction we also include an estimate of the prediction error, or uncertainty – i.e. how certain the algorithms are that the predicted value is correct. We appreciate that higher resolution does not necessarily equate to higher accuracy, which is why we communicate the uncertainty. R-squared values for each model can be found here.
For users of the iSDAsoil API, uncertainty is returned at 3 different confidence intervals, representing 50%, 68% (1 standard deviation) and 90% quantile intervals. These confidence intervals are defined using an upper and lower boundary value, which captures the percentage chance that the predicted value falls between these two values. The closer the upper and lower boundary values to the predicted value, the more certain the prediction, with 50% representing the most stringent threshold, and 90% representing the least.
When creating models for each soil property, we had minimal accuracy thresholds. Where the predictive models weren’t accurate enough to give useful data, the soil property was not included.
-
What does “Variability” mean on the maps?
The “Variability” displayed on the map refers to 1 standard deviation on either side of the predicted value, capturing 68% of the total variability of the prediction (see previous question for explanation of confidence intervals).
-
How do you standardise results generated through different laboratories and techniques?
We have used harmonization methods based on the literature, as well as expert input from researchers at Rothamsted Research. Many of the data points were from projects that used similar analytical techniques and were therefore directly comparable. We have done as much as we can to reduce errors and to harmonise the data.
For a more detailed description of the method used, see the technical information page.
-
Can I search a location by latitude and longitude?
Yes, the API accepts lat/lon queries. You can also search on the iSDAsoil map by providing the lat,lon as comma-separated values.
-
Is bulk data download available?
Yes. We have uploaded all of the soil property layers are covariates used in the predictions to the AWS Registry of Open Data. For more information, visit https://www.isda-africa.com/isdasoil/isdasoil-on-aws/
-
Can I download the data just for my local area, region or country?
Yes. You can use the data on the AWS Registry of Open Data to do this – visit the iSDAsoil on AWS page for more details.
-
How is the data licenced?
All data are freely available under a Creative Commons Attribution 4.0 International License.
-
I have another question that wasn’t answered here: how do I get in touch?
If you have any another questions, you can contact us via email.
*indicates data were log-scaled before modelling