Mapping Soil Properties of Africa at 250 m Resolution: Random Forests Significantly Improve Current Predictions

Abstract

80% of arable land in Africa has low soil fertility and suffers from physical soil problems. Additionally, significant amounts of nutrients are lost every year due to unsustainable soil management practices. This is partially the result of insufficient use of soil management knowledge. To help bridge the soil information gap in Africa, the Africa Soil Information Service (AfSIS) project was established in 2008. Over the period 2008–2014, the AfSIS project compiled two point data sets: the Africa Soil Profiles (legacy) database and the AfSIS Sentinel Site database. These data sets contain over 28 thousand sampling locations and represent the most comprehensive soil sample data sets of the African continent to date. Utilizing these point data sets in combination with a large number of covariates, we have generated a series of spatial predictions of soil properties relevant to the agricultural management—organic carbon, pH, sand, silt and clay fractions, bulk density, cation-exchange capacity, total nitrogen, exchangeable acidity, Al content and exchangeable bases (Ca, K, Mg, Na). We specifically investigate differences between two predictive approaches: random forests and linear regression. Results of 5-fold cross-validation demonstrate that the random forests algorithm consistently outperforms the linear regression algorithm, with average decreases of 15–75% in Root Mean Squared Error (RMSE) across soil properties and depths. Fitting and running random forests models takes an order of magnitude more time and the modelling success is sensitive to artifacts in the input data, but as long as quality-controlled point data are provided, an increase in soil mapping accuracy can be expected. Results also indicate that globally predicted soil classes (USDA Soil Taxonomy, especially Alfisols and Mollisols) help improve continental scale soil property mapping, and are among the most important predictors. This indicates a promising potential for transferring pedological knowledge from data rich countries to countries with limited soil data.

Multiple linear regression and random forest to predict and map soil properties using data from portable X-ray fluorescence spectrometer (pXRF)

“…However, despite of classifying the variables according to their importance to the model (Archer;Kimes, 2008), this method does not generate a final equation of the model, as opposed to SMLR. Therefore, it is sometimes referred to as a black-box method (Grimm et al, 2008), although some works have pointed out that this method is robust and provides better results than other methods for both spatial and non-spatial predictions (Hengl et al, 2015;Lies;Glaser;Huwe, 2012;Souza et al, 2016).…”

No Silver Bullet for Digital Soil Mapping: Country-specific Soil Organic Carbon Estimates across Latin America

“…Machine learning (i.e., data driven) models have proven to be more efficient to model non-linear relationships of SOC (Hengl et al, 2015), but our results suggest that linear-based models (e.g., RK) could outperform machine learning methods under well distributed and representative SOC data scenarios. Similar results were found 30 across productive landscapes of Brazil (Bonfatti et al, 2016).…”

Farmlands Feature Greater Woody Cover than Savannas in Semi-Arid West Africa

“…Out of these, mean annual rainfall 25 is the major factor limiting woody cover (32%). It is followed by terrain (elevation, 23%) and human population density 26 is ranked third (13%), shortly before soil 27 (sand fraction, 12%) and interannual rainfall variability (12%). Distance to villages (6%) and fire frequency (2%) have a rather low relative weight.…”

“…This difference is most pronounced in the semi-arid Sahel (conservation 16%; conservation surroundings 11%) and sub-humid zone (conservation 35%; conservation surround-ings 23%). Differences between farmland (typically occupying sandy soils) and savannas (including vast areas of non-arable soils) become more comparable when studying woody vegetation on sandy soils only 27 . Sandy soils used for cultivation have remarkably higher woody cover than comparable sandy soils which are uncultivated (Fig.…”