Journal cover Journal topic
SOIL An interactive open-access journal of the European Geosciences Union
https://doi.org/10.5194/soil-2017-13
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 3.0 License.
Original research article
19 Apr 2017
Review status
This discussion paper is a preprint. A revision of this manuscript was accepted for the journal SOIL (SOIL) and is expected to appear here in due course.
Mapping of soil properties at high resolution in Switzerland using boosted geoadditive models
Madlene Nussbaum1, Lorenz Walthert2, Marielle Fraefel2, Lucie Greiner3, and Andreas Papritz1 1Institute of Biogeochemistry and Pollutant Dynamics, ETH Zurich, Universitätstrasse 16, 8092 Zürich, Switzerland
2Swiss Federal Institute for Forest, Snow and Landscape Research (WSL), Zürcherstrasse 111, 8903 Birmensdorf, Switzerland
3Research Station Agroscope Reckenholz-Taenikon ART, Reckenholzstrasse 191, 8046 Zürich, Switzerland
Abstract. High-resolution maps of soil properties are a prerequisite for assessing soil threats and soil functions and to foster sustainable use of soil resources. For many regions in the world precise maps of soil properties are missing, but often sparsely sampled and discontinuous (legacy) soil data are available. Soil property data (response) can then be related by digital soil mapping (DSM) to spatially exhaustive environmental data that describe soil forming factors (covariates) to create spatially continuous maps. With air- and spaceborne remote sensing data and multi-scale terrain analysis large sets of covariates have become common. Building parsimonious models, amenable to pedological interpretation, is then a challenging task.

We propose a new boosted geoadditive modelling framework (geoGAM) for DSM. A geoGAM models smooth nonlinear relations between responses and single covariates and combines these model terms additively. Residual spatial autocorrelation is captured by a smooth function of spatial coordinates and nonstationary effects are included by interactions between covariates and smooth spatial functions. The core of fully automated model building for geoGAM is componentwise gradient boosting.

We illustrate the application of the geoGAM framework by using soil data from the Canton of Zurich, Switzerland. We modelled effective cation exchange capacity (ECEC) in forest topsoils as continuous response. For agricultural land we predicted the presence of waterlogged horizons in given soil depth layers as binary and drainage classes as ordinal responses. For the latter we used proportional odds geoGAM taking the ordering of the response properly into account. Fitted geoGAM contained only few covariates (7 to 17) selected from large sets (333 covariates for forests, 498 for agricultural land). Model sparsity allowed covariate interpretation by partial effects plots. Prediction intervals were computed by model-based bootstrapping for ECEC. Predictive performance of the fitted geoGAM, tested with independent validation data and specific skill scores (SS) for continuous, binary and ordinal responses, compared well with other studies that modelled similar soil properties. SS of 0.23 up to 0.53 (with SS = 1 for perfect predictions and SS = 0 for zero explained variance) were achieved depending on response and type of score. geoGAM combines efficient model building from large sets of covariates with ease of effect interpretation and therefore likely raises the acceptance of DSM products by end-users.


Citation: Nussbaum, M., Walthert, L., Fraefel, M., Greiner, L., and Papritz, A.: Mapping of soil properties at high resolution in Switzerland using boosted geoadditive models, SOIL Discuss., https://doi.org/10.5194/soil-2017-13, in review, 2017.
Madlene Nussbaum et al.
Interactive discussionStatus: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version      Supplement - Supplement
 
RC1: 'Reviewer's Comments', Anonymous Referee #1, 03 Jul 2017 Printer-friendly Version 
AC1: 'Answer to comments of referee 1', Madlene Nussbaum, 03 Sep 2017 Printer-friendly Version Supplement 
 
RC2: 'Soil 2017 13', Anonymous Referee #2, 08 Aug 2017 Printer-friendly Version 
AC2: 'Answer to comments of referee 2', Madlene Nussbaum, 03 Sep 2017 Printer-friendly Version Supplement 
Madlene Nussbaum et al.
Madlene Nussbaum et al.

Viewed

Total article views: 418 (including HTML, PDF, and XML)

HTML PDF XML Total Supplement BibTeX EndNote
259 144 15 418 29 7 11

Views and downloads (calculated since 19 Apr 2017)

Cumulative views and downloads (calculated since 19 Apr 2017)

Viewed (geographical distribution)

Total article views: 418 (including HTML, PDF, and XML)

Thereof 416 with geography defined and 2 with unknown origin.

Country # Views %
  • 1

Saved

Discussed

Latest update: 18 Oct 2017
Publications Copernicus
Download
Short summary
Digital soil mapping (DSM) relates soil property data to environmental data that describe soil forming factors. With imagery sampled from satellites or terrain analysed at multiple scales large sets of possible input to DSM is available. We propose a new statistical framework (geoGAM) that selects parsimonious models for DSM and illustrate geoGAM for 2 study regions. Straightforward interpretation of the modelled effects likely improves end-users’ acceptance for DSM products.
Digital soil mapping (DSM) relates soil property data to environmental data that describe soil...
Share