<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

African soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning

dc.contributor.authorTomislav Hengl
dc.contributor.authorMatthew A. E. Miller
dc.contributor.authorJosip Križan
dc.contributor.authorKeith D. Shepherd
dc.contributor.authorAndrew Sila
dc.contributor.authorMilan Kilibarda
dc.contributor.authorOgnjen Antonijević
dc.contributor.authorLuka Glušica
dc.contributor.authorAchim Dobermann
dc.contributor.authorStephan M. Haefele
dc.contributor.authorSteve P. McGrath
dc.contributor.authorGifty E. Acquah
dc.contributor.authorJamie Collinson
dc.contributor.authorLeandro Parente
dc.contributor.authorMohammadreza Sheykhmousa
dc.contributor.authorKazuki Saito
dc.contributor.authorJean-Martial Johnson
dc.contributor.authorJordan Chamberlin
dc.contributor.authorFrancis B. T. Silatsa
dc.contributor.authorMartin Yemefack
dc.contributor.authorJohn Wendt
dc.contributor.authorRobert A. MacMillan
dc.contributor.authorIchsani Wheeler
dc.contributor.authorJonathan Crouch
dc.date.accessioned2026-11-18T07:09:20Z
dc.date.issued2021
dc.descriptionOfficial PMC article XML states CC BY 4.0 and permits use, sharing, adaptation, distribution and reproduction with attribution. Rights classification: FULL_TEXT_OK. Licence verified from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7969779/ (checked 2026-11-18). Source: grid.435643.30000 0000 9972 1350World Agroforestry (ICRAF), Nairobi, Kenya; Africa Rice Center (AfricaRice), Bouaké, Côte d’Ivoire; International Maize and Wheat Improvement Centre (CIMMYT), Nairobi, Kenya; Sustainable Tropical Solutions (STS) Sarl, Yaoundéc, Cameroon African relevance: Sector: Agriculture. Two-scale ensemble ML produces 30 m soil property and nutrient maps for all of Africa from about 150,000 samples and Earth observation data. Official PMC article XML states CC BY 4.0 and permits use, sharing, adaptation, distribution and reproduction with attribution.
dc.description.abstractSoil property and class maps for the continent of Africa were so far only available at very generalised scales, with many countries not mapped at all. Thanks to an increasing quantity and availability of soil samples collected at field point locations by various government and/or NGO funded projects, it is now possible to produce detailed pan-African maps of soil nutrients, including micro-nutrients at fine spatial resolutions. In this paper we describe production of a 30 m resolution Soil Information System of the African continent using, to date, the most comprehensive compilation of soil samples (N≈150,000) and Earth Observation data. We produced predictions for soil pH, organic carbon (C) and total nitrogen (N), total carbon, effective Cation Exchange Capacity (eCEC), extractable—phosphorus (P), potassium (K), calcium (Ca), magnesium (Mg), sulfur (S), sodium (Na), iron (Fe), zinc (Zn)—silt, clay and sand, stone content, bulk density and depth to bedrock, at three depths (0, 20 and 50 cm) and using 2-scale 3D Ensemble Machine Learning framework implemented in the mlr (Machine Learning in R) package. As covariate layers we used 250 m resolution (MODIS, PROBA-V and SM2RAIN products), and 30 m resolution (Sentinel-2, Landsat and DTM derivatives) images. Our fivefold spatial Cross-Validation results showed varying accuracy levels ranging from the best performing soil pH (CCC = 0.900) to more poorly predictable extractable phosphorus (CCC = 0.654) and sulphur (CCC = 0.708) and depth to bedrock. Sentinel-2 bands SWIR (B11, B12), NIR (B09, B8A), Landsat SWIR bands, and vertical depth derived from 30 m resolution DTM, were the overall most important 30 m resolution covariates. Climatic data images—SM2RAIN, bioclimatic variables and MODIS Land Surface Temperature—however, rem
dc.format.mimetypeapplication/pdf
dc.identifier.doi10.1038/s41598-021-85639-y
dc.identifier.urihttps://doi.org/10.1038/s41598-021-85639-y
dc.identifier.urihttps://library.dare.co.zw/handle/123456789/5076
dc.language.isoen
dc.publisherNature Publishing Group
dc.rightsCC BY 4.0. Licence evidence: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7969779/
dc.rights.holderNamed authors
dc.rights.licenseCC BY 4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.sourcegrid.435643.30000 0000 9972 1350World Agroforestry (ICRAF), Nairobi, Kenya; Africa Rice Center (AfricaRice), Bouaké, Côte d’Ivoire; International Maize and Wheat Improvement Centre (CIMMYT), Nairobi, Kenya; Sustainable Tropical Solutions (STS) Sarl, Yaoundéc, Cameroon
dc.source.urihttps://doi.org/10.1038/s41598-021-85639-y
dc.subjectAgriculture
dc.subjectGeochemistry
dc.subjectMachine learning
dc.subjectBiogeochemistry
dc.subjectMineralogy
dc.subjectAgroecology
dc.subjectScientific Reports
dc.titleAfrican soil properties and nutrients mapped at 30 m spatial resolution using two-scale ensemble machine learning
dc.typejournal article

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
applied_agriculture_10_1038_s41598_021_85639_y.pdf
Size:
4.7 MB
Format:
Adobe Portable Document Format