Mapping Soil Properties of Africa at 250 m Resolution: Random Forests Significantly Improve Current Predictions
By Tomislav Hengl, Gerard B. M. Heuvelink, Bas Kempen, J. Leenaars, M. Walsh, Keith D. Shepherd, Andrew Sila, R. MacMillan, Jorge Mendes de Jesus, L. Tamene and 1 more. PLoS ONE, 2015
794 citations recorded by the source corpus.
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.
Subfields: Environmental Engineering, Management, Monitoring, Policy and Law, Soil Science
View Paper: https://www.semanticscholar.org/paper/8f66e29d0c21d7e04265349df41b51a86cdb4509
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Environmental Engineering
In Soil Science
- Marshall Burke
- David B. Lobell
- George Azzari
- Thomas W. Hertel
- W. Schlenker
- Salvatore Di Falco
- X. Ju
- P. Christie
Citations in the corpus
- Smallholder maize area and yield mapping at national scales with Google Earth Engine (2019, methodology): “Briefly, this product is generated using an ensemble of two machine learning algorithms with extensive training data of soil samples from>50,000 locations and a large stack of GIS layers that proximate soil forming processes (e.g. climate, topography, lithology and vegetation) (Hengl et al., 2015).”
- Soil Erosion Risk Assessment in Uganda (2017, methodology): “Soil erodibility factor of Uganda (Figure 4b) was estimated based on the sand, clay, silt and organic carbon fractions compiled by the Africa Soil Information Service (AfSIS) [39] using Equation (3) proposed by Williams (1995) [38,40,41].”