Telemark University College

About: Telemark University College is a based out in . It is known for research contribution in the topics: Population & Beaver. The organization has 423 authors who have published 759 publications receiving 20580 citations.

Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree

Abstract: Preparation of landslide susceptibility maps is considered as the first important step in landslide risk assessments, but these maps are accepted as an end product that can be used for land use planning. The main objective of this study is to explore some new state-of-the-art sophisticated machine learning techniques and introduce a framework for training and validation of shallow landslide susceptibility models by using the latest statistical methods. The Son La hydropower basin (Vietnam) was selected as a case study. First, a landslide inventory map was constructed using the historical landslide locations from two national projects in Vietnam. A total of 12 landslide conditioning factors were then constructed from various data sources. Landslide locations were randomly split into a ratio of 70:30 for training and validating the models. To choose the best subset of conditioning factors, predictive ability of the factors were assessed using the Information Gain Ratio with 10-fold cross-validation technique. Factors with null predictive ability were removed to optimize the models. Subsequently, five landslide models were built using support vector machines (SVM), multi-layer perceptron neural networks (MLP Neural Nets), radial basis function neural networks (RBF Neural Nets), kernel logistic regression (KLR), and logistic model trees (LMT). The resulting models were validated and compared using the receive operating characteristic (ROC), Kappa index, and several statistical evaluation measures. Additionally, Friedman and Wilcoxon signed-rank tests were applied to confirm significant statistical differences among the five machine learning models employed in this study. Overall, the MLP Neural Nets model has the highest prediction capability (90.2 %), followed by the SVM model (88.7 %) and the KLR model (87.9 %), the RBF Neural Nets model (87.1 %), and the LMT model (86.1 %). Results revealed that both the KLR and the LMT models showed promising methods for shallow landslide susceptibility mapping. The result from this study demonstrates the benefit of selecting the optimal machine learning techniques with proper conditioning selection method in shallow landslide susceptibility mapping.

The Natural Environment as a Playground for Children: The Impact of Outdoor Play Activities in Pre-Primary School Children

Abstract: have experienced positive results from being outdoorsin natural environments, but only a few studies haveNorwegian studies have revealed a disquieting ten-been done in this field (Bang et al, 1989; Fjortoft, 1999;dency that children are becoming more sedentary inGrahn et al, 1997) We know far too little about howtheir adolescence They spend more time, approximatelythe natural environment functions as a playground forthree hours a day, on TV, video, and electronic mediachildren, and we know even less about what effects such(MMI, 1995) The movement pattern of children hasa playground might have on learning in children Thechanged remarkably the last 10–20 years The unorgani-physical outdoor environment, and the natural environ-sed traditional games, which included lots of movingment in particular, as a play habitat for children, hasaround, are now changing into sitting in front of yourbeen a topic of low priority in child research (Bjerke,private computer playing computer games Such scenar-1994)ios have resulted in several health hazards like increas-ing obesity in early childhood (Anderson et al, 1998),and motor problems in children are reported in several

Ecological impact of beavers Castor fiber and Castor canadensis and their ability to modify ecosystems

Abstract: The genus Castor comprises two species: the Eurasian beaver Castor fibre , and the North American beaver Castor canadensis . Both species suffered from overexploitation, but have seen a revival since the 1920s due to increased protection and reintroduction programmes. Increases in the populations and distributions of species that are able to modify ecosystems have generated much scientific interest. Here we review the available literature concerning the possible ecological impact of beaver species in the Old and New World. 2. Beavers, being ecosystem engineers, are among the few species besides humans that can significantly change the geomorphology, and consequently the hydrological characteristics and biotic properties of the landscape. In so doing, beavers increase heterogeneity, and habitat and species diversity at the landscape scale. Beaver foraging also has a considerable impact on the course of ecological succession, species composition and structure of plant commu- nities, making them a good example of ecologically dominant species (e.g. keystone species). 3. Nevertheless, the strength of beavers' impact varies from site to site, depending on the geographical location, relief and the impounded habitat type. Consequently, they may not be significant controlling agents of the ecosystem in all parts of their distribution, but have strong interactions only under certain circumstances. We suggest that beavers can create important management opportunities in the Holarctic, and this review will help land man- agers determine the likely outcome of beaver activity.