Digital soil mapping using soilgrids and national soil data in Cameroon

Francis Silatsa Tedou

doi:10.1201/9781351239707-8

Digital soil mapping using soilgrids and national soil data in Cameroon

Francis Silatsa Tedou

ISRIC - World Soil Information

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review

Abstract

This study evaluates the SoilGrids as predictor, using point data from the Cameroon national soil profiles data compilation, together with a set of covariates representing soil forming factors. Much effort was placed on the preparation of the Cameroon soil database (‘Camsodat 0.1’). We predicted Soil Organic Carbon (SOC) and clay content at 250 m resolution in the test region (North Region of Cameroon), at standard GlobalSoilMap depths. Random forest regression provided models fitting with R2 up to 0.59. The inclusion of SoilGrids as additional covariates could slightly improve predictions with R2 up to 0.61.

Original language	English
Title of host publication	GlobalSoilMap - Digital Soil Mapping from Country to Globe
Subtitle of host publication	Proceedings of the Global Soil Map 2017 Conference, July 4-6, 2017, Moscow, Russia
Editors	Dominique Arrouays, Igor Savin, Johan Leenaars, Alex B. McBratney
Publisher	CRC Press
Chapter	8
Number of pages	6
ISBN (Electronic)	9781351239707
DOIs	https://doi.org/10.1201/9781351239707-8
Publication status	Published - 2017

Access to Document

10.1201/9781351239707-8

1 Book editing

GlobalSoilMap - Digital Soil Mapping from Country to Globe: Proceedings of the Global Soil Map 2017 Conference, July 4-6, 2017, Moscow, Russia
Arrouays, D. (Editor), Savin, I. (Editor), Leenaars, J. G. B. (Editor) & McBratney, A. B. (Editor), 28 Nov 2017, CRC Press. 174 p.
Research output: Book/Report › Book editing › Academic

Cite this

@inbook{802f093579534cdf9f6093d28d45b3c9,

title = "Digital soil mapping using soilgrids and national soil data in Cameroon",

abstract = "This study evaluates the SoilGrids as predictor, using point data from the Cameroon national soil profiles data compilation, together with a set of covariates representing soil forming factors. Much effort was placed on the preparation of the Cameroon soil database ({\textquoteleft}Camsodat 0.1{\textquoteright}). We predicted Soil Organic Carbon (SOC) and clay content at 250 m resolution in the test region (North Region of Cameroon), at standard GlobalSoilMap depths. Random forest regression provided models fitting with R2 up to 0.59. The inclusion of SoilGrids as additional covariates could slightly improve predictions with R2 up to 0.61.",

author = "\{Silatsa Tedou\}, Francis",

year = "2017",

doi = "10.1201/9781351239707-8",

language = "English",

editor = "Arrouays, \{Dominique \} and Savin, \{Igor \} and Leenaars, \{Johan \} and McBratney, \{Alex B. \}",

booktitle = "GlobalSoilMap - Digital Soil Mapping from Country to Globe",

publisher = "CRC Press",

address = "United States",

}

Digital soil mapping using soilgrids and national soil data in Cameroon. / Silatsa Tedou, Francis.
GlobalSoilMap - Digital Soil Mapping from Country to Globe: Proceedings of the Global Soil Map 2017 Conference, July 4-6, 2017, Moscow, Russia. ed. / Dominique Arrouays; Igor Savin; Johan Leenaars; Alex B. McBratney. CRC Press, 2017.

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Academic › peer-review

TY - CHAP

T1 - Digital soil mapping using soilgrids and national soil data in Cameroon

AU - Silatsa Tedou, Francis

PY - 2017

Y1 - 2017

N2 - This study evaluates the SoilGrids as predictor, using point data from the Cameroon national soil profiles data compilation, together with a set of covariates representing soil forming factors. Much effort was placed on the preparation of the Cameroon soil database (‘Camsodat 0.1’). We predicted Soil Organic Carbon (SOC) and clay content at 250 m resolution in the test region (North Region of Cameroon), at standard GlobalSoilMap depths. Random forest regression provided models fitting with R2 up to 0.59. The inclusion of SoilGrids as additional covariates could slightly improve predictions with R2 up to 0.61.

AB - This study evaluates the SoilGrids as predictor, using point data from the Cameroon national soil profiles data compilation, together with a set of covariates representing soil forming factors. Much effort was placed on the preparation of the Cameroon soil database (‘Camsodat 0.1’). We predicted Soil Organic Carbon (SOC) and clay content at 250 m resolution in the test region (North Region of Cameroon), at standard GlobalSoilMap depths. Random forest regression provided models fitting with R2 up to 0.59. The inclusion of SoilGrids as additional covariates could slightly improve predictions with R2 up to 0.61.

U2 - 10.1201/9781351239707-8

DO - 10.1201/9781351239707-8

M3 - Chapter

BT - GlobalSoilMap - Digital Soil Mapping from Country to Globe

A2 - Arrouays, Dominique

A2 - Savin, Igor

A2 - Leenaars, Johan

A2 - McBratney, Alex B.

PB - CRC Press

ER -

Digital soil mapping using soilgrids and national soil data in Cameroon

Abstract

Access to Document

Fingerprint

Research output

GlobalSoilMap - Digital Soil Mapping from Country to Globe: Proceedings of the Global Soil Map 2017 Conference, July 4-6, 2017, Moscow, Russia

Cite this