- Dataset Availability
- Dataset Provider
- Earth Engine Snippet
Sign up for Earth Engine
Earth Engine is free to use for research, education, and nonprofit use.
To access this dataset in Earth Engine, please sign up for Earth Engine then return to this page.
Depth to bedrock at 0-200 cm depth, predicted mean and standard deviation.
Due to the potential cropland mask that was used for generating the data, many areas of exposed rock (where depth to bedrock would be 0 cm) have been masked out and therefore appear as nodata values. The maximum depth of this layer is 200 cm, but this does not represent the maximum possible soil depth, therefore values of 200 should be interpreted as >= 200.
In areas of dense jungle (generally over central Africa), model accuracy is low and therefore artifacts such as banding (striping) might be seen.
Soil property predictions were made by Innovative Solutions for Decision Agriculture Ltd. (iSDA) at 30 m pixel size using machine learning coupled with remote sensing data and a training set of over 100,000 analyzed soil samples.
Depth to bedrock, predicted mean at 0-200 cm depth
Depth to bedrock, standard deviation at 0-20 cm depth
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). doi:10.1038/s41598-021-85639-y