iSDAsoil: soil fine-earth bulk density for Africa predicted at 30 m resolution at 0-20 and 20-50 cm depths
DOI10.5281/zenodo.4087905Zenodo4087905MaRDI QIDQ6688856FDOQ6688856
Dataset published at Zenodo repository.
Josip Križan, Andrew M. Sila, Gifty Acquah, Tomislav Hengl, Matt Miller, Milan Kilibarda
Publication date: 14 October 2020
Copyright license: Creative Commons Attribution 4.0 International
iSDAsoil dataset soil fine-earth bulk density in 10kg/m3 predicted at 30 m resolution for 020 and 2050 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, LandPKS, 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 30m spatial resolution using two-scale ensemble machine learning.Sci Rep11,6130 (2021). https://doi.org/10.1038/s41598-021-85639-y To open the maps in QGIS and/or directly compute with them, please use the Cloud-Optimized GeoTIFF version. Layer description: sol_db_od_m_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil bulk density mean value, sol_db_od_md_30m_*..*cm_2001..2017_v0.13_wgs84.tif = predicted soil bulk density 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: db_od R-square: 0.819 Fitted values sd: 0.269 RMSE: 0.126 Random forest model: Call: stats::lm(formula = f, data = d) Residuals: Min 1Q Median 3Q Max -1.06778 -0.06450 0.00215 0.06585 0.90016 Coefficients: Estimate Std. Error t value Pr(|t|) (Intercept) -0.05538 0.04860 -1.140 0.25451 regr.ranger 0.86305 0.01577 54.733 2e-16 * regr.xgboost 0.15383 0.01651 9.315 2e-16 * regr.cubist 0.02039 0.01113 1.832 0.06695 . regr.nnet 0.03465 0.03710 0.934 0.35036 regr.cvglmnet -0.03021 0.01032 -2.927 0.00343 --- Signif. codes: 0 '*' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 0.1263 on 13565 degrees of freedom Multiple R-squared: 0.8194, Adjusted R-squared: 0.8193 F-statistic: 1.231e+04 on 5 and 13565 DF, p-value: 2.2e-16 To back-transform values (y) to kg/m-cubic use: kg/m3 = y * 10 To submit an issue or request support please visit https://isda-africa.com/isdasoil
This page was built for dataset: iSDAsoil: soil fine-earth bulk density for Africa predicted at 30 m resolution at 0-20 and 20-50 cm depths
