dc.contributor.author | Martin, M.P. | |
dc.contributor.author | Orton, T.G. | |
dc.contributor.author | Lacarce, E. | |
dc.contributor.author | Meersmans, J | |
dc.contributor.author | Saby, N.P.A. | |
dc.contributor.author | Paroissien, J.B. | |
dc.contributor.author | Jolivet, C. | |
dc.contributor.author | Boulonne, L. | |
dc.contributor.author | Arrouays, D. | |
dc.date.accessioned | 2015-09-23T12:00:28Z | |
dc.date.issued | 2014-07 | |
dc.description.abstract | 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. © 2014 Elsevier B.V. | en_GB |
dc.description.sponsorship | French Scientific Group of Interest on soils: the GIS Sol | en_GB |
dc.description.sponsorship | French Ministry of Ecology, Sustainable Development and Energy (MEDDE) | en_GB |
dc.description.sponsorship | French Ministry of Agriculture, Food and Forestry (MAAF) | en_GB |
dc.description.sponsorship | French Agency for Environment and Energy Management (ADEME) | en_GB |
dc.description.sponsorship | Institute for Research and Development (IRD) | en_GB |
dc.description.sponsorship | National Institute of Geographic and Forest Information (IGN) | en_GB |
dc.description.sponsorship | National Institute for Agronomic Research (INRA) | en_GB |
dc.description.sponsorship | EU project “Greenhouse gas management in European land use systems (GHG-Europe)” | en_GB |
dc.identifier.citation | Vol. 223-225, pp. 97 - 107 | en_GB |
dc.identifier.doi | 10.1016/j.geoderma.2014.01.005 | |
dc.identifier.grantnumber | FP7-ENV-2009-1-244122 | en_GB |
dc.identifier.uri | http://hdl.handle.net/10871/18304 | |
dc.language.iso | en | en_GB |
dc.publisher | Elsevier | en_GB |
dc.rights | Accepted manuscript: © 2014, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ | en_GB |
dc.subject | Boosted regression trees | en_GB |
dc.subject | Geostatistics | en_GB |
dc.subject | National accounting | en_GB |
dc.subject | Soil organic carbon | en_GB |
dc.subject | Spatial distributions | en_GB |
dc.title | Evaluation of modelling approaches for predicting the spatial distribution of soil organic carbon stocks at the national scale | en_GB |
dc.type | Article | en_GB |
dc.date.available | 2015-09-23T12:00:28Z | |
dc.identifier.issn | 0016-7061 | |
dc.description | Copyright © 2014 Elsevier. NOTICE: this is the author’s version of a work that was accepted for publication in Geoderma. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Geoderma (2014), DOI: 10.1016/j.geoderma.2014.01.005 | en_GB |
dc.identifier.eissn | 1872-6259 | |
dc.identifier.journal | Geoderma | en_GB |