Refine
Has Fulltext
- no (3)
Year of publication
- 2012 (3) (remove)
Document Type
- Article (3) (remove)
Language
- English (3)
Is part of the Bibliography
- yes (3)
Keywords
Institute
Detailed knowledge on the spatial distribution of soils is crucial for environmental monitoring, management, and modeling. However soil maps with a finite number of discrete soil map units are often the only available information about soils. Depending on the map scale or the detailing of the map legend this information could be too imprecise. We present a method for the spatial disaggregation of map units, namely the refinement of complex soil map units in which two or more soil types are aggregated. Our aim is to draw new boundaries inside the map polygons to represent a single soil type and no longer a mixture of several soil types. The basic idea for our method is the functional relationship between soil types and topographic position as formulated in the concept of the catena. We use a comprehensive soil profile database and topographic attributes derived from a 10 m digital elevation model as input data for the classification of soil types with random forest models. We grouped all complex map units which have the same combination of soil types. Each group of map units is modeled separately. For prediction of the soil types we stratified the soil map into these groups and apply a specific random forest model only to the associated map units. In order to get reliable results we define a threshold for the predicted probabilities at 0.7 to assign a specific soil type. In areas where the probability is below 0.7 for every possible soil type we assign a new class "indifferent" because the model only makes unspecific classification there. Our results show a significant spatial refinement of the original soil polygons. Validation of our predictions was estimated on 1812 independent soil profiles which were collected subsequent to prediction in the field. Field validation gave an overall accuracy of 70%. Map units, in which shallow soils were grouped together with deep soils could be separated best. Also histosols could be predicted successful. Highest error rate were found in map units, in which Gleysoils were grouped together with deep soils or Anthrosols. To check for validity of our results we open the black box random forest model by calculating the variable importance for each predictor variable and plotting response surfaces. We found good confirmations of our hypotheses, that topography has a significant influence on the spatial arrangement of soil types and that these relationships can be used for disaggregation.
Landslides are a hazard for humans and artificial structures. From an ecological point of view, they represent an important ecosystem disturbance, especially in tropical montane forests. Here, shallow translational landslides are a frequent natural phenomenon and one local determinant of high levels of biodiversity. In this paper, we apply weighted ensembles of advanced phenomenological models from statistics and machine learning to analyze the driving factors of natural landslides in a tropical montane forest in South Ecuador. We exclusively interpret terrain attributes, derived from a digital elevation model, as proxies to several driving factors of landslides and use them as predictors in our models which are trained on a set of five historical landslide inventories. We check the model generality by transferring them in time and use three common performance criteria (i.e. AUC, explained deviance and slope of model calibration curve) to, on the one hand, compare several state-of-the-art model approaches and on the other hand, to create weighted model ensembles. Our results suggest that it is important to consider more than one single performance criterion.
Approaching our main question, we compare responses of weighted model ensembles that were trained on distinct functional units of landslides (i.e. initiation, transport and deposition zones). This way, we are able to show that it is quite possible to deduce driving factors of landslides, if the consistency between the training data and the processes is maintained. Opening the 'black box' of statistical models by interpreting univariate model response curves and relative importance of single predictors regarding their plausibility, we provide a means to verify this consistency.
With the exception of classification tree analysis, all techniques performed comparably well in our case study while being outperformed by weighted model ensembles. Univariate response curves of models trained on distinct functional units of landslides exposed different shapes following our expectations. Our results indicate the occurrence of landslides to be mainly controlled by factors related to the general position along a slope (i.e. ridge, open slope or valley) while landslide initiation seems to be favored by small scale convexities on otherwise plain open slopes.
Empirical species distribution models (SDMs) constitute often the tool of choice for the assessment of rapid climate change effects on species vulnerability. Conclusions regarding extinction risks might be misleading, however, because SDMs do not explicitly incorporate dispersal or other demographic processes. Here, we supplement SDMs with a dynamic population model 1) to predict climate-induced range dynamics for black grouse in Switzerland, 2) to compare direct and indirect measures of extinction risks, and 3) to quantify uncertainty in predictions as well as the sources of that uncertainty. To this end, we linked models of habitat suitability to a spatially explicit, individual-based model. In an extensive sensitivity analysis, we quantified uncertainty in various model outputs introduced by different SDM algorithms, by different climate scenarios and by demographic model parameters. Potentially suitable habitats were predicted to shift uphill and eastwards. By the end of the 21st century, abrupt habitat losses were predicted in the western Prealps for some climate scenarios. In contrast, population size and occupied area were primarily controlled by currently negative population growth and gradually declined from the beginning of the century across all climate scenarios and SDM algorithms. However, predictions of population dynamic features were highly variable across simulations. Results indicate that inferring extinction probabilities simply from the quantity of suitable habitat may underestimate extinction risks because this may ignore important interactions between life history traits and available habitat. Also, in dynamic range predictions uncertainty in SDM algorithms and climate scenarios can become secondary to uncertainty in dynamic model components. Our study emphasises the need for principal evaluation tools like sensitivity analysis in order to assess uncertainty and robustness in dynamic range predictions. A more direct benefit of such robustness analysis is an improved mechanistic understanding of dynamic species responses to climate change.