Predicting forest attributes In southeast Alaska using artificial neural networks

Artificial neural network (ANN) methods are used to predict forest characteristics. The data source is the Southeast Alaska (SEAK) Grid Inventory, a ground survey compiled by the USDA Forest Service at several thousand sites. The main objective of this article is to predict characteristics at unsurveyed locations between grid sites. A secondary objective is to evaluate the relative performance of different ANNs. Data from the grid sites are used to train six ANNs: multilayer perceptron, fuzzy ARTMAP, probabilistic, generalized regression, radial basis function, and learning vector quantization. A classification and regression tree method is used for comparison. Topographic variables are used to construct models: latitude and longitude coordinates, elevation, slope, and aspect. The models classify three forest characteristics: crown closure, species land cover, and tree size/structure. Models are constructed using n-fold cross-validation. Predictive accuracy is calculated using a method that accounts for the influence of misclassification as well as measuring correct classifications. The probabilistic and generalized regression networks are found to be the most accurate. The predictions of the ANN models are compared with a classification of the Tongass national forest in southeast Alaska based on the interpretation of satellite imagery and are found to be of similar accuracy.

The impact of the summer 2007 forest fires in Greece: Recent environmental mobilizations, cyber-activism and electoral performance

This report circumambulates around the environmental issue, examining mobilizations in favour of public access to the seafront and protest events against the recent devastating forest fires. By framing this discussion within existing scholarly contributions on related dimensions of the environmental issue (environmental consciousness, grassroots environmental contestation) in Southern Europe in general and Greece in particular, it suggests that the environmental mobilization dynamic in Greece has been infused with a new, global, mobilizing resource that offers new avenues to evaluate the potency of Greek civil society. Finally, the article discusses the results of the 2007 national elections and ponders the chances of political ecology becoming a permanent feature of Greek parliamentary politics.

Mitochondrial DNA haplotype analysis of liver fluke in bison from Bialowieza Primaeval Forest indicates domestic cattle as the likely source of infection

We have determined the mitochondrial genotype of liver fluke present in Bison (Bison bonasus) from the herd maintained in the Bialowieza National Park in order to determine the origin of the infection. Our results demonstrated that the infrapopulations present in the bison were genetically diverse and were likely to have been derived from the population present in local cattle. From a consideration of the genetic structure of the liver fluke infrapopulations we conclude that the provision of hay at feeding stations may be implicated in the transmission of this parasite to the bison. This information may be of relevance to the successful management of the herd. © 2012 Elsevier B.V.