ALBERT

Beschreibung: High-resolution maps of soil properties are a prerequisite for assessing soil threats and soil functions and for fostering the sustainable use of soil resources. For many regions in the world, accurate maps of soil properties are missing, but often sparsely sampled (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 airborne and space-borne remote sensing 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. The geoGAM models smooth non-linear 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 non-stationary effects are included through interactions between covariates and smooth spatial functions. The core of fully automated model building for geoGAM is component-wise 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 a continuous response. For agricultural land we predicted the presence of waterlogged horizons in given soil depths 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 a few covariates (7 to 17) selected from large sets (333 covariates for forests, 498 for agricultural land). Model sparsity allowed for covariate interpretation through partial effects plots. Prediction intervals were computed by model-based bootstrapping for ECEC. The predictive performance of the fitted geoGAM, tested with independent validation data and specific skill scores for continuous, binary and ordinal responses, compared well with other studies that modelled similar soil properties. Skill score (SS) values of 0.23 to 0.53 (with SS = 1 for perfect predictions and SS = 0 for zero explained variance) were achieved depending on the response and type of score. GeoGAM combines efficient model building from large sets of covariates with effects that are easy to interpret and therefore likely raises the acceptance of DSM products by end-users.

Beschreibung: Spatial information on soil function fulfillment (SFF) is increasingly being used to inform decision-making in spatial planning programs to support sustainable use of soil resources. Soil function maps visualize soils abilities to fulfill their functions, e.g., regulating water and nutrient flows, providing habitats, and supporting biomass production based on soil properties. Such information must be reliable for informed and transparent decision-making in spatial planning programs. In this study, we add to the transparency of soil function maps by (1) indicating uncertainties arising from the prediction of soil properties generated by digital soil mapping (DSM) that are used for soil function assessment (SFA) and (2) showing the response of different SFA methods to the propagation of uncertainties through the assessment. For a study area of 170 km2 in the Swiss Plateau, we map 10 static soil sub-functions for agricultural soils for a spatial resolution of 20 × 20 m together with their uncertainties. Mapping the 10 soil sub-functions using simple ordinal assessment scales reveals pronounced spatial patterns with a high variability of SFF scores across the region, linked to the inherent properties of the soils and terrain attributes and climate conditions. Uncertainties in soil properties propagated through SFA methods generally lead to substantial uncertainty in the mapped soil sub-functions. We propose two types of uncertainty maps that can be readily understood by stakeholders. Cumulative distribution functions of SFF scores indicate that SFA methods respond differently to the propagated uncertainty of soil properties. Even where methods are comparable on the level of complexity and assessment scale, their comparability in view of uncertainty propagation might be different. We conclude that comparable uncertainty indications in soil function maps are relevant to enable informed and transparent decisions on the sustainable use of soil resources.

Beschreibung: Spatial assessment of soil functions requires maps of basic soil properties. Unfortunately, these are either missing for many regions or are not available at the desired spatial resolution or down to required soil depth. Conventional soil map generation remains costly. Field based generation of large soil data sets and of conventional soil maps remains costly. Meanwhile, soil legacy data and comprehensive sets of spatial environmental data are available for many regions. Digital soil mapping (DSM) approaches – relating soil data (responses) to environmental data (covariates) – are facing the challenge to build statistical models from large sets of covariates originating for example from airborne imaging spectroscopy or multi-scale terrain analysis. We evaluated six approaches for DSM in three study regions in Switzerland (Berne, Greifensee, ZH forest) by mapping effective soil depth available to plants (SD), pH, soil organic matter (SOM), effective cation exchange capacity (ECEC), clay, silt, gravel content and bulk density for four soil layers (totalling 48 responses). Models were built from 300–500 environmental covariates by selecting linear models by (1) grouped lasso and by an ad-hoc stepwise procedure for (2) robust external-drift kriging (EDK). For (3) geoadditive models we selected penalized smoothing spline terms by componentwise gradient boosting (geoGAM). We further used two tree-based methods: (4) boosted regression trees (BRT) and (5) Random Forest (RF). Lastly, we computed (6) weighted model averages (MA) from predictions obtained from methods 1–5. Lasso, georob and geoGAM successfully selected strongly reduced sets of covariates (subsets of 3–6 % of all covariates). To automatically select a sparse trend model for EDK was however difficult, and the applied ad hoc procedure was computationally inefficient and over-fitted the data. Differences in predictive performance, tested on independent validation data, were mostly small and did not reveal a single best method for 48 responses. Nevertheless, RF was on average often best among methods 1–5 (28 of 48 responses), but was outcompeted by MA for 14 of these 28 responses. RF tended to over-fit the data. Performance of BRT was slightly worse than RF. GeoGAM performed poorly on some responses and was only best for 7 of 48 responses. Predictive precision of lasso was intermediate. All models generally had small bias. Only the computationally very efficient lasso had slightly larger bias likely because it tended to under-fit the data. Summarizing, although differences were small, the frequencies of best and worst performance clearly favoured RF if a single method is applied MA if multiple prediction models can be developed.

Beschreibung: 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.

Beschreibung: The mapping of soil functions is increasingly being used to inform decision-making in spatial planning processes related to the capacity of soils to contribute to ecosystem services. In this study, we add to the transparency of soil function maps by indicating uncertainties arising from prediction uncertainties of soil properties as generated by digital soil mapping (DSM). For a study area in the Swiss Midlands, we map 10 static soil functions for agricultural soils together with their uncertainties, using soil property data generated by DSM. Mapping the ten soil functions using simple ordinal assessment scales reveals pronounced spatial patterns with a high variability of soil function fulfillment (SFF) across the region, linked to the inherent properties of the soils and terrain attributes and climate conditions. Uncertainties in soil properties propagated through SFA methods generally lead to substantial uncertainty in the mapped soil functions. We propose two types of uncertainty maps that can be readily understood by stakeholders. Cumulative distribution functions of SFF scores indicate that SFA methods respond differently to the propagated uncertainty of soil properties. Even where methods are comparable on the level of complexity and assessment scale, their comparability in view of uncertainty propagation might be different. We conclude that uncertainty indications in soil function maps are required to enable informed and transparent decisions on the sustainable use of soil resources.

Beschreibung: The spatial assessment of soil functions requires maps of basic soil properties. Unfortunately, these are either missing for many regions or are not available at the desired spatial resolution or down to the required soil depth. The field-based generation of large soil datasets and conventional soil maps remains costly. Meanwhile, legacy soil data and comprehensive sets of spatial environmental data are available for many regions.Digital soil mapping (DSM) approaches relating soil data (responses) to environmental data (covariates) face the challenge of building statistical models from large sets of covariates originating, for example, from airborne imaging spectroscopy or multi-scale terrain analysis. We evaluated six approaches for DSM in three study regions in Switzerland (Berne, Greifensee, ZH forest) by mapping the effective soil depth available to plants (SD), pH, soil organic matter (SOM), effective cation exchange capacity (ECEC), clay, silt, gravel content and fine fraction bulk density for four soil depths (totalling 48 responses). Models were built from 300–500 environmental covariates by selecting linear models through (1) grouped lasso and (2) an ad hoc stepwise procedure for robust external-drift kriging (georob). For (3) geoadditive models we selected penalized smoothing spline terms by component-wise gradient boosting (geoGAM). We further used two tree-based methods: (4) boosted regression trees (BRTs) and (5) random forest (RF). Lastly, we computed (6) weighted model averages (MAs) from the predictions obtained from methods 1–5.Lasso, georob and geoGAM successfully selected strongly reduced sets of covariates (subsets of 3–6 % of all covariates). Differences in predictive performance, tested on independent validation data, were mostly small and did not reveal a single best method for 48 responses. Nevertheless, RF was often the best among methods 1–5 (28 of 48 responses), but was outcompeted by MA for 14 of these 28 responses. RF tended to over-fit the data. The performance of BRT was slightly worse than RF. GeoGAM performed poorly on some responses and was the best only for 7 of 48 responses. The prediction accuracy of lasso was intermediate. All models generally had small bias. Only the computationally very efficient lasso had slightly larger bias because it tended to under-fit the data. Summarizing, although differences were small, the frequencies of the best and worst performance clearly favoured RF if a single method is applied and MA if multiple prediction models can be developed.