iSDAsoil: soil extractable Magnesium for Africa predicted at 30 m resolution at 0-20 and 20-50 cm depths

iSDAsoil dataset soil extractable Magnesium (Mg) log-transformed predicted at 30 m resolution for 0–20 and 20–50 cm depth intervals. Data has been projected in WGS84 coordinate system and compiled as COG. Predictions have been generated using multi-scale Ensemble Machine Learning with 250 m (MODIS, PROBA-V, climatic variables and similar) and 30 m (DTM derivatives, Landsat, Sentinel-2 and similar) resolution covariates. For model training we use a pan-African compilations of soil samples and profiles (iSDA points, AfSPDB, and other national and regional soil datasets). Cite as:

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/s41…

To open the maps in QGIS and/or directly compute with them, please use the Cloud-Optimized GeoTIFF ver….

Layer description:

• sol_log.mg_mehlich3_m_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil extractable Magnesium mean value,
• sol_log.mg_mehlich3_md_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil extractable Magnesium model (prediction) errors,

Model errors were derived using bootstrapping: md is derived as standard deviation of individual learners from 5-fold cross-validation (using spatial blocking). The model 5-fold cross-validation (mlr::makeStackedLearner) for this variable indicates:

Variable: log.mg_mehlich3 
R-square: 0.815 
Fitted values sd: 1.05 
RMSE: 0.498 

Random forest model:
Call:
stats::lm(formula = f, data = d)

Residuals:
    Min      1Q  Median      3Q     Max 
-5.8775 -0.2312  0.0028  0.2465  3.7400 

Coefficients:
               Estimate Std. Error t value Pr(>|t|)    
(Intercept)   -0.034349   0.051219  -0.671   0.5025    
regr.ranger    1.034217   0.003263 316.950   <2e-16 ***
regr.xgboost  -0.008057   0.003854  -2.091   0.0366 *  
regr.cubist    0.073223   0.003649  20.067   <2e-16 ***
regr.nnet     -0.017388   0.009528  -1.825   0.0680 .  
regr.cvglmnet -0.075566   0.003402 -22.213   <2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 0.4979 on 136681 degrees of freedom
Multiple R-squared:  0.8152,	Adjusted R-squared:  0.8152 
F-statistic: 1.206e+05 on 5 and 136681 DF,  p-value: < 2.2e-16

To back-transform values (y) to ppm use the following formula:

ppm = expm1( y / 10 )

To submit an issue or request support please visit https://isda-africa.com/isd…

iSDA is a social enterprise founded by – Rothamsted Research, the World Agroforestry (ICRAF) and the International Institute of Tropical Agriculture (IITA) – building on the legacy of the AfSIS project to create financially sustainable agronomy solutions for smallholder farmers. We are grateful to all national soil agencies especially GhaSIS, TanSIS, EthioSIS and NiSIS for providing soil sampling data and technical support.