Evaluation of modelling approaches for predicting the spatial distribution of soil organic carbon stocks at the national scale - INRAE - Institut national de recherche pour l’agriculture, l’alimentation et l’environnement Accéder directement au contenu
Article Dans Une Revue Geoderma Année : 2014

Evaluation of modelling approaches for predicting the spatial distribution of soil organic carbon stocks at the national scale

Manuel Martin P.
Connectez-vous pour contacter l'auteur
Eva Lacarce
  • Fonction : Auteur
Nicolas N. Saby
Claudy C. Jolivet
Line Boulonne
Dominique D. Arrouays

Résumé

Soil organic carbon (SOC) plays a major role in the global carbon budget. It can act as a source or a sink of atmospheric carbon, thereby possibly influencing the course of climate change. Improving the tools that model the spatial distributions of SOC stocks at national scales is a priority, both for monitoring changes in SOC and as an input for global carbon cycles studies. In this paper, we compare and evaluate two recent and promising modelling approaches. First, we considered several increasingly complex boosted regression trees (BRT), a convenient and efficient multiple regression model from the statistical learning field. Further, we considered a robust geostatistical approach coupled to the BRT models. Testing the different approaches was performed on the dataset from the French Soil Monitoring Network, with a consistent cross-validation procedure. We showed that when a limited number of predictors were included in the BRT model, the standalone BRT predictions were significantly improved by robust geostatistical modelling of the residuals. However, when data for several SOC drivers were included, the standalone BRT model predictions were not significantly improved by geostatistical modelling. Therefore, in this latter situation, the BRT predictions might be considered adequate without the need for geostatistical modelling, provided that i) care is exercised in model fitting and validating, and ii) the dataset does not allow for modelling of local spatial autocorrelations, as is the case for many national systematic sampling schemes. (C) 2014 Elsevier B.V. All rights reserved.

Dates et versions

hal-02639547 , version 1 (28-05-2020)

Identifiants

Citer

Manuel Martin P., T. G. Orton, Eva Lacarce, Jeroen Meersmans, Nicolas N. Saby, et al.. Evaluation of modelling approaches for predicting the spatial distribution of soil organic carbon stocks at the national scale. Geoderma, 2014, 223-225, pp.97 - 107. ⟨10.1016/j.geoderma.2014.01.005⟩. ⟨hal-02639547⟩
55 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More