HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Figures Only Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via Google Scholar Google Scholar Articles by Martin, M. P. Articles by Arrouays, D. Search for Related Content PubMed Articles by Martin, M. P. Articles by Arrouays, D. GeoRef GeoRef Citation Agricola Articles by Martin, M. P. Articles by Arrouays, D. Related Collections Structure and Properties Pedotransfer Functions

SOIL PHYSICS

Optimizing Pedotransfer Functions for Estimating Soil Bulk Density Using Boosted Regression Trees

^a INRA, Unité Infosol, 2163 Ave Pomme de Pin, BP 20619, F-45166 Olivet, France
^b CIRAD-ES, UMR TETIS (Cemagref–CIRAD–ENGREF), 34093 Montpellier, Cedex 5, France
^c National Bureau of Soil Survey and Land Use Planning, Hebbal, Bangalore 560 024, India
^d CIRAD-PERSYST, UR Environmental Risks of Recycling, 34398 Montpellier, Cedex 5, France

^* Corresponding author (manuel.martin{at}orleans.inra.fr).

Pedotransfer functions (PTFs) are used to estimate certain soil properties that are difficult and costly to measure from others more easily available. Bulk density is one important soil property. Although not requiring complex analysis, its measurement remains time consuming and is lacking in many soil surveys. For several decades, PTFs have been developed for predicting soil bulk density. Most of these PTFs are suited only for specific agro-pedo-climatic conditions, however, and can be applied only within a limited geographic area. In this study, we derived and experimented with two new PTFs based on a multiple additive regression trees (MART) method, and assessed their performance compared with existing PTFs when applied to a country-level soil database, the Réseau de Mesures de la Qualité des Sols (RMQS) survey network. This database was designed to include the major soil types and land uses in France. The first proposed PTF (Model m) involves only three predictors typically found in the existing PTFs for bulk density (C content and texture) and the second one (Model M) includes eight easily accessible quantitative and qualitative predictors (e.g., soil taxon). Both models significantly outperformed existing PTFs. Without arbitrarily partitioning the data set before fitting the model, the m and M MART models yielded R² values of 0.83 and 0.94, respectively. The predictive quality on independent data, assessed using cross-validation, was also improved compared with published PTFs, with R² reaching 0.62 and 0.66 and root mean square prediction errors of 0.123 and 0.117 Mg m^–3 for the two MART models.

Abbreviations: BF, bag fraction • CE, coarse element • LC, land cover • LR, learning rate • MART, multiple additive regression tree • min.obs, minimum number of observation in the terminal leaves of the trees • Model m, the MART model involving three predictors • Model M, the MART model involving eight predictors • MPE, mean prediction error • OC, organic carbon • PTF, pedotransfer function • RMQS, Réseau de Mesure de la Qualité des Sols • RMSPE, root mean square prediction error • SDPE, standard deviation of the prediction error • TS, tree size