scholarly journals Mapping of soil properties at high resolution in Switzerland using boosted geoadditive models

2017 ◽  
Author(s):  
Madlene Nussbaum ◽  
Lorenz Walthert ◽  
Marielle Fraefel ◽  
Lucie Greiner ◽  
Andreas Papritz
Keyword(s):  
High Resolution ◽  
Soil Properties ◽  
Agricultural Land ◽  
Model Building ◽  
Soil Depth ◽  
Environmental Data ◽  
Gradient Boosting ◽  
Validation Data ◽  
Large Sets ◽  
Skill Scores

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.

scholarly journals Mapping of soil properties at high resolution in Switzerland using boosted geoadditive models

SOIL ◽  
2017 ◽  
Vol 3 (4) ◽  
pp. 191-210 ◽  
Author(s):  
Madlene Nussbaum ◽  
Lorenz Walthert ◽  
Marielle Fraefel ◽  
Lucie Greiner ◽  
Andreas Papritz
Keyword(s):  
High Resolution ◽  
Soil Properties ◽  
Agricultural Land ◽  
Model Building ◽  
Environmental Data ◽  
Gradient Boosting ◽  
Terrain Analysis ◽  
Validation Data ◽  
Large Sets ◽  
Skill Scores

Abstract. 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.

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

SOIL ◽  
2018 ◽  
Vol 4 (1) ◽  
pp. 1-22 ◽  
Author(s):  
Madlene Nussbaum ◽  
Kay Spiess ◽  
Andri Baltensweiler ◽  
Urs Grob ◽  
Armin Keller ◽  
...  
Keyword(s):  
Prediction Models ◽  
Soil Depth ◽  
Fine Fraction ◽  
Soil Mapping ◽  
Environmental Data ◽  
Boosted Regression Trees ◽  
Gradient Boosting ◽  
Validation Data ◽  
Environmental Covariates ◽  
Large Sets

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.

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

2017 ◽  
Author(s):  
Madlene Nussbaum ◽  
Kay Spiess ◽  
Andri Baltensweiler ◽  
Urs Grob ◽  
Armin Keller ◽  
...  
Keyword(s):  
Ad Hoc ◽  
Soil Depth ◽  
Soil Mapping ◽  
Environmental Data ◽  
Digital Soil Mapping ◽  
Boosted Regression Trees ◽  
Gradient Boosting ◽  
Validation Data ◽  
Environmental Covariates ◽  
Large Sets

Abstract. 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.

Changes in soil properties on agricultural land with the impact of water and tillage erosion in the last 60 years

2020 ◽  
Author(s):  
Anna Juřicová ◽  
Tomáš Chuman ◽  
Daniel Žížala
Keyword(s):  
Spatial Variability ◽  
Soil Properties ◽  
Large Scale ◽  
Agricultural Land ◽  
Environmental Changes ◽  
Soil Depth ◽  
Field Investigation ◽  
Strong Impact ◽  
The Impact ◽  
Tillage Erosion

<p>The decline in soil organic carbon (SOC) is generally perceived as a major threat to the sustainability of the soil due to its key role in many productive and non - productive soil functions. The aim of this research is to assess the intensity of changes and the spatial variability of SOC and soil depth in the last 60 years. Estimation of spatial variability of soil properties was performed by using digital soil mapping. A study area is located in the chernozems area in south Moravia (Czechia). This region is traditionally intensively cultivated with the strong impact of water and tillage erosion. The study is based on the analysis of historical data that comes from the Large-scale mapping of Agricultural Soils in Czechoslovakia soil database. Our dataset contained data from 120 soil profiles. A new field investigation shows significant SOC losses on steep slopes and slope shoulders with a decrease of depth of the humic horizon. As a result, there is a gradual transformation of soil units from the former Calcic Chernosems into the Haplic Calcisols. These findings are the result of ongoing environmental changes with the strong impact of historical agricultural policy and inappropriate interference in the landscape.</p>

scholarly journals Fine-Resolution Mapping of Soil Total Nitrogen across China Based on Weighted Model Averaging

2019 ◽  
Vol 12 (1) ◽  
pp. 85 ◽  
Author(s):  
Yue Zhou ◽  
Jie Xue ◽  
Songchao Chen ◽  
Yin Zhou ◽  
Zongzheng Liang ◽  
...  
Keyword(s):  
Total Nitrogen ◽  
Soil Depth ◽  
Arable Land ◽  
Model Averaging ◽  
Nutrient Status ◽  
Gradient Boosting ◽  
Validation Data ◽  
Data Set ◽  
Extreme Gradient Boosting ◽  
Weighted Model

Accurate estimates of the spatial distribution of total nitrogen (TN) in soil are fundamental for soil quality assessment, decision making in land management, and global nitrogen cycle modeling. In China, current maps are limited to individual regions or are of coarse resolution. In this study, we compiled a new 90-m resolution map of soil TN in China by the weighted summation of random forest and extreme gradient boosting. After harmonizing soil data from 4022 soil profiles into a fixed soil depth (0–20 cm) by equal area spline, 18 environmental covariates were employed to characterize the spatial pattern of soil TN in topsoil across China. The accuracy assessments from independent validation data showed that the weighted model averaging gave the best predictions with an acceptable R2 (0.41). The prediction map showed that high-value areas of soil TN were mainly distributed in the eastern Tibetan Plateau, central Qilian Mountains and the north of the Greater Khingan Range. Climate factors had a considerable influence on the variation of the soil TN, and land-use types played a pivotal part in each climate zone. This high-resolution and high-quality soil TN data set in China can be very useful for future inventories of soil nitrogen, assessments of soil nutrient status, and management of arable land.

scholarly journals Patient-Specific Predictive Antibiogram in Decision Support for Empiric Antibiotic Treatment

2020 ◽  
Vol 41 (S1) ◽  
pp. s521-s522
Author(s):  
Debarka Sengupta ◽  
Vaibhav Singh ◽  
Seema Singh ◽  
Dinesh Tewari ◽  
Mudit Kapoor ◽  
...  
Keyword(s):  
Machine Learning ◽  
Antimicrobial Resistance ◽  
Model Building ◽  
Medical Center ◽  
Bacterial Species ◽  
Model Performance ◽  
The United States ◽  
Patient Specific ◽  
Gradient Boosting ◽  
Comparative Performance

Background: The rising trend of antibiotic resistance imposes a heavy burden on healthcare both clinically and economically (US$55 billion), with 23,000 estimated annual deaths in the United States as well as increased length of stay and morbidity. Machine-learning–based methods have, of late, been used for leveraging patient’s clinical history and demographic information to predict antimicrobial resistance. We developed a machine-learning model ensemble that maximizes the accuracy of such a drug-sensitivity versus resistivity classification system compared to the existing best-practice methods. Methods: We first performed a comprehensive analysis of the association between infecting bacterial species and patient factors, including patient demographics, comorbidities, and certain healthcare-specific features. We leveraged the predictable nature of these complex associations to infer patient-specific antibiotic sensitivities. Various base-learners, including k-NN (k-nearest neighbors) and gradient boosting machine (GBM), were used to train an ensemble model for confident prediction of antimicrobial susceptibilities. Base learner selection and model performance evaluation was performed carefully using a variety of standard metrics, namely accuracy, precision, recall, F1 score, and Cohen κ. Results: For validating the performance on MIMIC-III database harboring deidentified clinical data of 53,423 distinct patient admissions between 2001 and 2012, in the intensive care units (ICUs) of the Beth Israel Deaconess Medical Center in Boston, Massachusetts. From ~11,000 positive cultures, we used 4 major specimen types namely urine, sputum, blood, and pus swab for evaluation of the model performance. Figure 1 shows the receiver operating characteristic (ROC) curves obtained for bloodstream infection cases upon model building and prediction on 70:30 split of the data. We received area under the curve (AUC) values of 0.88, 0.92, 0.92, and 0.94 for urine, sputum, blood, and pus swab samples, respectively. Figure 2 shows the comparative performance of our proposed method as well as some off-the-shelf classification algorithms. Conclusions: Highly accurate, patient-specific predictive antibiogram (PSPA) data can aid clinicians significantly in antibiotic recommendation in ICU, thereby accelerating patient recovery and curbing antimicrobial resistance.Funding: This study was supported by Circle of Life Healthcare Pvt. Ltd.Disclosures: None

scholarly journals Earthworms as an Ecological Indicator of Soil Recovery after Mechanized Logging Operations in Mixed Beech Forests

Forests ◽  
2020 ◽  
Vol 12 (1) ◽  
pp. 18
Author(s):  
Hadi Sohrabi ◽  
Meghdad Jourgholami ◽  
Mohammad Jafari ◽  
Farzam Tavankar ◽  
Rachele Venanzi ◽  
...  
Keyword(s):  
Soil Properties ◽  
Soil Depth ◽  
Biological Properties ◽  
Economic Benefits ◽  
Ecological Indicator ◽  
Traffic Intensity ◽  
Soil Biological Properties ◽  
Density And Biomass ◽  
Soil Recovery ◽  
The Impact

Soil damage caused by logging operations conducted to obtain and maximize economic benefits has been established as having long-term effects on forest soil quality and productivity. However, a comprehensive study of the impact of logging operations on earthworms as a criterion for soil recovery has never been conducted in the Hyrcanian forests of Iran. The aim of this study was to determine the changes in soil biological properties (earthworm density and biomass) and its recovery process under the influence of traffic intensity, slope and soil depth in various intervals according to age after logging operations. Soil properties were compared among abandoned skid trails with different ages (i.e., 3, 10, 20, and 25 years) and an undisturbed area. The results showed that earthworm density and biomass in the high traffic intensity and slope class of 20–30% at the 10–20 cm depth of the soil had the lowest value compared to the other treatments. Twenty-five years after the logging operations, the earthworm density at soil depth of 0–10 and 10–20 cm was 28.4% (0.48 ind. m−2) and 38.6% (0.35 ind. m−2), which were less than those of the undisturbed area, respectively. Meanwhile, the earthworm biomass at a soil depth of 0–10 and 10–20 cm was 30.5% (2.05 mg m−2) and 40.5% (1.54 mg m−2) less than the values of the undisturbed area, respectively. The earthworm density and biomass were positively correlated with total porosity, organic carbon and nitrogen content, while negatively correlated with soil bulk density and C/N ratio. According to the results, 25 years after logging operations, the earthworm density and biomass on the skid trails were recovered, but they were significantly different with the undisturbed area. Therefore, full recovery of soil biological properties (i.e., earthworm density and biomass) takes more than 25 years. The conclusions of our study reveal that the effects of logging operations on soil properties are of great significance, and our understanding of the mechanism of soil change and recovery demand that harvesting operations be extensively and properly implemented.

scholarly journals A Place-Based Approach to Agricultural Nonmaterial Intangible Cultural Ecosystem Service Values

2020 ◽  
Vol 12 (2) ◽  
pp. 699 ◽  
Author(s):  
Joy R. Petway ◽  
Yu-Pin Lin ◽  
Rainer F. Wunderlich
Keyword(s):  
Land Cover ◽  
Ecosystem Service ◽  
Agricultural Landscape ◽  
Agricultural Land ◽  
Environmental Data ◽  
Farming Practices ◽  
Environmental Characteristics ◽  
Cultural Ecosystem Service ◽  
Context Specific ◽  
Landscape Biodiversity

Though agricultural landscape biodiversity and ecosystem service (ES) conservation is crucial to sustainability, agricultural land is often underrepresented in ES studies, while cultural ES associated with agricultural land is often limited to aesthetic and tourism recreation value only. This study mapped 7 nonmaterial-intangible cultural ES (NICE) valuations of 34 rural farmers in western Taiwan using the Social Values for Ecosystem Services (SolVES) methodology, to show the effect of farming practices on NICE valuations. However, rather than a direct causal relationship between the environmental characteristics that underpin ES, and respondents’ ES valuations, we found that environmental data is not explanatory enough for causality within a socio-ecological production landscape where one type of land cover type (a micro mosaic of agricultural land cover) predominates. To compensate, we used a place-based approach with Google Maps data to create context-specific data to inform our assessment of NICE valuations. Based on 338 mapped points of 7 NICE valuations distributed among 6 areas within the landscape, we compared 2 groups of farmers and found that farmers’ valuations about their landscape were better understood when accounting for both the landscape’s cultural places and environmental characteristics, rather than environmental characteristics alone. Further, farmers’ experience and knowledge influenced their NICE valuations such that farm areas were found to be sources of multiple NICE benefits demonstrating that farming practices may influence ES valuation in general.

Very high resolution environmental predictors in species distribution models

2013 ◽  
Vol 38 (1) ◽  
pp. 79-96 ◽  
Author(s):  
Jean-Nicolas Pradervand ◽  
Anne Dubuis ◽  
Loïc Pellissier ◽  
Antoine Guisan ◽  
Christophe Randin
Keyword(s):  
High Resolution ◽  
Species Distribution ◽  
Species Distribution Models ◽  
Environmental Data ◽  
Swiss Alps ◽  
Fine Scale ◽  
Distribution Models ◽  
Model Quality ◽  
Vegetation Height ◽  
Very High

Recent advances in remote sensing technologies have facilitated the generation of very high resolution (VHR) environmental data. Exploratory studies suggested that, if used in species distribution models (SDMs), these data should enable modelling species’ micro-habitats and allow improving predictions for fine-scale biodiversity management. In the present study, we tested the influence, in SDMs, of predictors derived from a VHR digital elevation model (DEM) by comparing the predictive power of models for 239 plant species and their assemblages fitted at six different resolutions in the Swiss Alps. We also tested whether changes of the model quality for a species is related to its functional and ecological characteristics. Refining the resolution only contributed to slight improvement of the models for more than half of the examined species, with the best results obtained at 5 m, but no significant improvement was observed, on average, across all species. Contrary to our expectations, we could not consistently correlate the changes in model performance with species characteristics such as vegetation height. Temperature, the most important variable in the SDMs across the different resolutions, did not contribute any substantial improvement. Our results suggest that improving resolution of topographic data only is not sufficient to improve SDM predictions – and therefore local management – compared to previously used resolutions (here 25 and 100 m). More effort should be dedicated now to conduct finer-scale in-situ environmental measurements (e.g. for temperature, moisture, snow) to obtain improved environmental measurements for fine-scale species mapping and management.

Sign in / Sign up

Export Citation Format

Share Document