African Soil Properties and Nutrients Mapped at 30--m Spatial Resolution using Two-scale Ensemble Machine Learning

Abstract

Soil property and class maps for the continent of Africa were so far only available at very generalised scales, with many countries not mappedat all. Thanks to an increasing quantity and availability of soil samples collected at field point locations by various government and/or NGOfunded projects, it is now possible to produce detailed pan-African maps of soil nutrients, including micro-nutrients at fine spatial resolutions. Inthis paper we describe production of a 30 m resolution Soil Information System of the African continent using, to date, the most comprehensivecompilation of soil samples (N ≈ 150, 000) and Earth Observation data. We produced predictions for soil pH, organic carbon (C) and totalnitrogen (N), total carbon, 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 and50 cm) and using 2-scale 3D Ensemble Machine Learning framework implemented in the mlr (Machine Learning in R) package. As covariatelayers we used 250 m resolution (MODIS, PROBA-V and SM2RAIN products), and 30 m resolution (Sentinel-2, Landsat and DTM derivatives)images. Our 5–fold spatial Cross-Validation results showed varying accuracy levels ranging from the best performing soil pH (CCC=0.900) tomore 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 mresolution covariates. Climatic data images — SM2RAIN, bioclimatic variables and MODIS Land Surface Temperature — however, remainedas the overall most important variables for predicting soil chemical variables at continental scale. The publicly available 30–m soil maps aresuitable for numerous applications, including soil and fertilizer policies and investments, agronomic advice to close yield gaps, environmentalprograms, or targeting of nutrition interventions.

Progress in research on site-specific nutrient management for smallholder farmers in sub-Saharan Africa

“…To address such complex interactions, it will likely be necessary to include additional geospatial information as well as rule-based algorithms in the existing SSNM solutions. A new 30-m resolution digital soil map is now free available for the entire content ( Hengl et al, 2021 ), which should be explored for such purposes. These maps could provide soil information such as soil texture, acidity, Mn and Al toxicity, soil erosion, and soil crusts, and adjust soil fertility and nutrient management practices (e.g.…”

Agricultural Technology in Africa

“…For example, the maize yield response to fertilizer is strongly dependent on sandiness and soil carbon content (Burke et al 2020). These land characteristics vary in important ways across communities, at scales as small as hundreds of meters: Hengl et al (2021) show some maps of data collected by the International Soil Reference and Information Centre (ISRIC), displaying differences in the soil acidity at a resolution of 30 meters. There is even substantial variation in soil characteristics within farms, and farmers adjust production decisions to accommodate that variation (for example, Tjernström et al 2015).…”

Agricultural data collection to minimize measurement error and maximize coverage

“…Thus, remote sensing and ground data are much more productively seen as complements rather than substitutes. The use of survey data, particularly objective measures such as crop cuts, for ground-truthing and training models based on satellite data can greatly increase the accuracy of the remote sensing predictions (see d'Andrimont, 2018;Paliwal andJain, 2020 for yield measurement andHengl et al, 2020 for global soil mapping). The combined use of multiple sources is the most promising avenue for agricultural data systems to minimize error and maximize coverage.…”