Impact of multi-scale predictor selection for modeling soil properties

Miller, Bradley A.; Koszinski, Sylvia; Wehrhan, Marc; Sommer, Michael

doi:10.1016/j.geoderma.2014.09.018

Cited by 120 publications

(75 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In general, the topographic factors with coarser grid resolutions and bigger neighbor extents, were more strongly related to five topsoil properties, namely, they had stronger explanatory power for those topsoil properties (Table 2), which supported the conclusions of previous researches [6,7].…”

Section: Correlation Analysis and Variable Selectionsupporting

confidence: 85%

Estimation of Forest Topsoil Properties Using Airborne LiDAR-Derived Intensity and Topographic Factors

Liu

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

Forest topsoil supports vegetation growth and contains the majority of soil nutrients that are important indices of soil fertility and quality. Therefore, estimating forest topsoil properties, such as soil organic matter (SOM), total nitrogen (Total N), pH, litter-organic (O-A) horizon depth (Depth) and available phosphorous (AvaP), is of particular importance for forest development and management. As an emerging technology, light detection and ranging (LiDAR) can capture the three-dimensional structure and intensity information of scanned objects, and can generate high resolution digital elevation models (DEM) using ground echoes. Moreover, great power for estimating forest topsoil properties is enclosed in the intensity information of ground echoes. However, the intensity has not been well explored for this purpose. In this study, we collected soil samples from 62 plots and the coincident airborne LiDAR data in a Korean pine forest in Northeast China, and assessed the effectiveness of both multi-scale intensity data and LiDAR-derived topographic factors for estimating forest topsoil properties. The results showed that LiDAR-derived variables could be robust predictors of four topsoil properties (SOM, Total N, pH, and Depth), with coefficients of determination (R 2 ) ranging from 0.46 to 0.66. Ground-returned intensity was identified as the most effective predictor for three topsoil properties (SOM, Total N, and Depth) with R 2 values of 0.17-0.64. Meanwhile, LiDAR-derived topographic factors, except elevation and sediment transport index, had weak explanatory power, with R 2 no more than 0.10. These findings suggest that the LiDAR intensity of ground echoes is effective for estimating several topsoil properties in forests with complicated topography and dense canopy cover. Furthermore, combining intensity and multi-scale LiDAR-derived topographic factors, the prediction accuracies (R 2 ) were enhanced by negligible amounts up to 0.40, relative to using intensity only for topsoil properties. Moreover, the prediction accuracy for Depth increased by 0.20, while for other topsoil properties, the prediction accuracies increased negligibly, when the scale dependency of soil-topography relationship was taken into consideration.

show abstract

Section: Correlation Analysis and Variable Selectionsupporting

confidence: 85%

Estimation of Forest Topsoil Properties Using Airborne LiDAR-Derived Intensity and Topographic Factors

Liu

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In georob uncertainties can be directly derived from the kriging variances. For RF, conditional quantiles of predictive distributions can be estimated directly at the cost of a larger memory requirement (R package quantregForest; Meinshausen, 2015). For lasso, geoGAM, BRT and MA, model-based bootstrapping can be used to simulate predictive distributions (see Nussbaum et al, 2017, for geoGAM uncertainties for topsoil ECEC), but bootstrapping involves quite some computational effort.…”

Section: Practical Use Of Statistical Methodsmentioning

confidence: 99%

“…Using comprehensive environmental geodata for DSM improves prediction accuracy because soil-forming factors are likely better represented by a larger number of covariates. Derivatives of geological or legacy soil maps (Nussbaum et al, 2014), multi-scale terrain analysis (Behrens et al, 2010a(Behrens et al, , b, 2014Miller et al, 2015), wide ranges of climatic parameters (Liddicoat et al, 2015) and (multi-temporal) imaging spectroscopy (Mulder et al, 2011;Poggio et al, 2013;Viscarra Rossel et al, 2015;Fitzpatrick et al, 2016;Hengl et al, 2017;Maynard and Levi, 2017) all contribute to generating high-dimensional sets of partly multi-collinear covariates. One usually presumes that DSM techniques benefit from a large number of covariates even if a method selects only a small subset of relevant covariates for creating the predictions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of digital soil mapping approaches with large sets of environmental covariates

Nussbaum¹,

Spiess²,

Baltensweiler³

et al. 2018

SOIL

214

View full text Add to dashboard Cite

Abstract. 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.Published by Copernicus Publications on behalf of the European Geosciences Union.

show abstract

“…In order to model the distribution of soil properties, we considered a set of 34 GISbased geographic covariates in the form of raster maps. As many terrain indices as possible were calculated because a large set of predictors can compensate unaccounted variables [13]. A full set of used terrain indices can be found in Fig 3. All terrain variables were averaged within the section of the mixed sample.…”

Section: Terrain Variablesmentioning

confidence: 99%

Comparison of terrain-based drift models to improve the quality of soil predictive mapping at a field scale

Ryazanov¹,

Sahabiev²

2016

Tomsk State University Journal of Biology

View full text Add to dashboard Cite

Comparison of terrain-based drift models to improve the quality of soil predictive mapping at a field scaleThe ecological, economic, and agricultural benefits of accurate interpolation of spatial distribution patterns of soil properties are well recognized. In the present study different approaches to build the drift model for the regression kriging are analyzed and compared for estimating the spatial variation of humus and physical clay at soil depth (0-20 cm) in Tatarstan, Russian Federation. The soil sampling was performed according to an agrochemical sampling design: the field was divided into 60 sections; within each section 12-15 sampling points were taken using a hand auger at the depth of 10-20 cm to produce one mixed sample. Three terrain-based drift models: principal component regression (PCR), partial least squares (PLS), and random forest were used to predict the spatial distribution of humus and physical clay. Cross-validation was applied to evaluate the accuracy of interpolation methods through mean error (ME), root mean square error (RMSE), root mean square standardized error (RMSSE), and ratio of the observed and the predicted variances (RVar). The results indicate that ordinary kriging (OK) is superior when the data have strong spatial dependence. But in other cases, the PLS approach had the best prediction performance.The article contains 4 Figures, 5 Tables,29 References. Keywords: spatial interpolation; prediction; geostatistics; regression kriging; humus; physical clay. IntroductionSpatial variability of soil properties is an important indicator of soil quality, and it is important in ecological modeling, environmental prediction, precision agriculture, and natural resource management [1]. Revealing the characteristics of spatial patterns will provide the basis for evaluating soil fertility, and assist in the development of sound agricultural management policies. So, there is a need for adequate information about spatio-temporal behavior of soil properties over a region and accurate interpolation at unsampled locations is needed for better planning and management.In general, there are two major approaches to predict soil properties at unsampled location. Methods of "classic" statistics use linear and non-linear regression models to predict dependent variable using auxiliary data. Remote sensing data, topographic and morphologic attributes, climate, land-use and 22 geology are auxiliary parameters commonly used for the calibration of predictive models. For example, Rodriquez-Lado and Martinez-Cortizas used multiple linear regression, e.g. principal component regression and partial least squares, for modeling and mapping organic carbon content of topsoil using climatic and geological data as independent variables [2].The second approach is geostatistics, which has been rapidly developing for last decades [3; 4]. Geostatistics is an efficient method for studying spatial allocation of soil characteristics and their inconsistency and reducing the variance of assessment error and execution costs [...

show abstract

Impact of multi-scale predictor selection for modeling soil properties

Cited by 120 publications

References 37 publications

Estimation of Forest Topsoil Properties Using Airborne LiDAR-Derived Intensity and Topographic Factors

Estimation of Forest Topsoil Properties Using Airborne LiDAR-Derived Intensity and Topographic Factors

Evaluation of digital soil mapping approaches with large sets of environmental covariates

Comparison of terrain-based drift models to improve the quality of soil predictive mapping at a field scale

Contact Info

Product

Resources

About