Mapping soil properties of Africa at 250 m resolution: random forests significantly improve current predictions

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 bridg...

Descripción completa

Detalles Bibliográficos
Autores principales: Hengl, Tomislav, Heuvelink, Gerard B.M., Kempen, Bas, Leenaars, Johan G.B., Walsh, Markus G., Shepherd, Keith D., Sila, Andrew M., MacMillan, Robert A, Mendes de Jesus, Jorge, Tamene, Lulseged D., Tondoh, Jérôme E.
Formato: Journal Article
Lenguaje:Inglés
Publicado: Public Library of Science 2015
Materias:
Acceso en línea:https://hdl.handle.net/10568/68703
_version_ 1855534345444392960
author Hengl, Tomislav
Heuvelink, Gerard B.M.
Kempen, Bas
Leenaars, Johan G.B.
Walsh, Markus G.
Shepherd, Keith D.
Sila, Andrew M.
MacMillan, Robert A
Mendes de Jesus, Jorge
Tamene, Lulseged D.
Tondoh, Jérôme E.
author_browse Hengl, Tomislav
Heuvelink, Gerard B.M.
Kempen, Bas
Leenaars, Johan G.B.
MacMillan, Robert A
Mendes de Jesus, Jorge
Shepherd, Keith D.
Sila, Andrew M.
Tamene, Lulseged D.
Tondoh, Jérôme E.
Walsh, Markus G.
author_facet Hengl, Tomislav
Heuvelink, Gerard B.M.
Kempen, Bas
Leenaars, Johan G.B.
Walsh, Markus G.
Shepherd, Keith D.
Sila, Andrew M.
MacMillan, Robert A
Mendes de Jesus, Jorge
Tamene, Lulseged D.
Tondoh, Jérôme E.
author_sort Hengl, Tomislav
collection Repository of Agricultural Research Outputs (CGSpace)
description 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.
format Journal Article
id CGSpace68703
institution CGIAR Consortium
language Inglés
publishDate 2015
publishDateRange 2015
publishDateSort 2015
publisher Public Library of Science
publisherStr Public Library of Science
record_format dspace
spelling CGSpace687032025-03-13T09:44:53Z Mapping soil properties of Africa at 250 m resolution: random forests significantly improve current predictions Hengl, Tomislav Heuvelink, Gerard B.M. Kempen, Bas Leenaars, Johan G.B. Walsh, Markus G. Shepherd, Keith D. Sila, Andrew M. MacMillan, Robert A Mendes de Jesus, Jorge Tamene, Lulseged D. Tondoh, Jérôme E. simulation models forecasting soil management soil chemicophysical properties statistical methods soil degradation acidity soil modelos de simulación técnicas de predicción manejo del suelo propiedades físico - químicas suelo metodos estadísticos degradación del suelo acidez suelo áfrica 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. 2015-05-23 2015-10-27T19:09:06Z 2015-10-27T19:09:06Z Journal Article https://hdl.handle.net/10568/68703 en Open Access Public Library of Science Hengl, Tomislav; Heuvelink, Gerard B. M.; Kempen, Bas; Leenaars, Johan G. B.; Walsh, Markus G.; Shepherd, Keith D.; Sila, Andrew; MacMillan, Robert A.; Mendes de Jesus, Jorge; Desta, Lulseged Tamene; Tondoh, Jérôme E.. 2015. Mapping soil properties of africa at 250 m resolution: random forests significantly improve current predictions . PLoS ONE 10(6): e0125814.
spellingShingle simulation models
forecasting
soil management
soil chemicophysical properties
statistical methods
soil degradation
acidity
soil
modelos de simulación
técnicas de predicción
manejo del suelo
propiedades físico - químicas suelo
metodos estadísticos
degradación del suelo
acidez
suelo
áfrica
Hengl, Tomislav
Heuvelink, Gerard B.M.
Kempen, Bas
Leenaars, Johan G.B.
Walsh, Markus G.
Shepherd, Keith D.
Sila, Andrew M.
MacMillan, Robert A
Mendes de Jesus, Jorge
Tamene, Lulseged D.
Tondoh, Jérôme E.
Mapping soil properties of Africa at 250 m resolution: random forests significantly improve current predictions
title Mapping soil properties of Africa at 250 m resolution: random forests significantly improve current predictions
title_full Mapping soil properties of Africa at 250 m resolution: random forests significantly improve current predictions
title_fullStr Mapping soil properties of Africa at 250 m resolution: random forests significantly improve current predictions
title_full_unstemmed Mapping soil properties of Africa at 250 m resolution: random forests significantly improve current predictions
title_short Mapping soil properties of Africa at 250 m resolution: random forests significantly improve current predictions
title_sort mapping soil properties of africa at 250 m resolution random forests significantly improve current predictions
topic simulation models
forecasting
soil management
soil chemicophysical properties
statistical methods
soil degradation
acidity
soil
modelos de simulación
técnicas de predicción
manejo del suelo
propiedades físico - químicas suelo
metodos estadísticos
degradación del suelo
acidez
suelo
áfrica
url https://hdl.handle.net/10568/68703
work_keys_str_mv AT hengltomislav mappingsoilpropertiesofafricaat250mresolutionrandomforestssignificantlyimprovecurrentpredictions
AT heuvelinkgerardbm mappingsoilpropertiesofafricaat250mresolutionrandomforestssignificantlyimprovecurrentpredictions
AT kempenbas mappingsoilpropertiesofafricaat250mresolutionrandomforestssignificantlyimprovecurrentpredictions
AT leenaarsjohangb mappingsoilpropertiesofafricaat250mresolutionrandomforestssignificantlyimprovecurrentpredictions
AT walshmarkusg mappingsoilpropertiesofafricaat250mresolutionrandomforestssignificantlyimprovecurrentpredictions
AT shepherdkeithd mappingsoilpropertiesofafricaat250mresolutionrandomforestssignificantlyimprovecurrentpredictions
AT silaandrewm mappingsoilpropertiesofafricaat250mresolutionrandomforestssignificantlyimprovecurrentpredictions
AT macmillanroberta mappingsoilpropertiesofafricaat250mresolutionrandomforestssignificantlyimprovecurrentpredictions
AT mendesdejesusjorge mappingsoilpropertiesofafricaat250mresolutionrandomforestssignificantlyimprovecurrentpredictions
AT tamenelulsegedd mappingsoilpropertiesofafricaat250mresolutionrandomforestssignificantlyimprovecurrentpredictions
AT tondohjeromee mappingsoilpropertiesofafricaat250mresolutionrandomforestssignificantlyimprovecurrentpredictions