%0 Journal Article
%9 ACL : Articles dans des revues avec comité de lecture répertoriées par l'AERES
%A Bahri, H.
%A Raclot, Damien
%A Barbouchi, M.
%A Lagacherie, P.
%A Annabi, M.
%T Mapping soil organic carbon stocks in Tunisian topsoils
%D 2022
%L fdi:010085883
%G ENG
%J Geoderma Regional
%@ 2352-0094
%K Digital soil mapping ; Soil organic carbon stocks ; Tunisian soils ; Quantile regression forest ; Machine learning spatial prediction ; National approach ; Multiple soil classes
%K TUNISIE
%M ISI:000831551000001
%P e00561 [10 ]
%R 10.1016/j.geodrs.2022.e00561
%U https://www.documentation.ird.fr/hor/fdi:010085883
%> https://www.documentation.ird.fr/intranet/publi/2022-09/010085883.pdf
%V 30
%W Horizon (IRD)
%X Better knowledge of the amount and spatial distribution of soil organic carbon (SOC) stock at national level is a key element for monitoring, planning and decision-making regarding soil quality management, agriculture or carbon storage options. The present study proposes for the first time a Digital Soil Mapping (DSM) initiative to map SOC stocks in Tunisian topsoils (0-30 cm) at 100 m resolution, using a Quantile Regression Forest (QRF) algorithm, a range of environmental covariates, and a national database of 1540 SOC stock profiles. Our results provided a revised assessment of the SOC stock on the Tunisian territory at 391Tg C in the first 30 cm of soil profile, i.e. an average of 2.53 kg m-2. The map of SOC stocks outperformed global DSM products such as SoilGrids 2.0 in both R2 (0.44 vs. 0.15) and RMSE (1.94 vs. 2.52 kg m-2) and can be used as a benchmark against changes of land use and climate. The importance of the environmental covariates tested indicates the major role of bioclimatic data and, to a lesser extent, remote sensing images and topography-related variables. Our study did not show a significant added value of using additional covariates in relation to nationally available variables or the SOC map predicted by SoilGrids2.0. Finally, our results showed that increasing the quality and quantity of soil profile observations is most likely the best way to improve the future SOC map, starting with the northern region of Tunisia, which has the highest SOC stock predictions and uncertainties in the country. An alternative way would be the exploration of new covariates through sub-national approaches.
%$ 068