Automatic Mapping and Classification of Spatial Environmental Data

The paper deals with the development and application of the generic methodology for automatic processing (mapping and classification) of environmental data. General Regression Neural Network (GRNN) is considered in detail and is proposed as an efficient tool to solve the problem of spatial data mapping (regression). The Probabilistic Neural Network (PNN) is considered as an automatic tool for spatial classifications. The automatic tuning of isotropic and anisotropic GRNN/PNN models using cross-validation procedure is presented. Results are compared with the k-Nearest-Neighbours (k-NN) interpolation algorithm using independent validation data set. Real case studies are based on decision-oriented mapping and classification of radioactively contaminated territories.

Comparison between artificial neural networks and maximum likelihood classification in digital soil mapping

Soil surveys are the main source of spatial information on soils and have a range of different applications, mainly in agriculture. The continuity of this activity has however been severely compromised, mainly due to a lack of governmental funding. The purpose of this study was to evaluate the feasibility of two different classifiers (artificial neural networks and a maximum likelihood algorithm) in the prediction of soil classes in the northwest of the state of Rio de Janeiro. Terrain attributes such as elevation, slope, aspect, plan curvature and compound topographic index (CTI) and indices of clay minerals, iron oxide and Normalized Difference Vegetation Index (NDVI), derived from Landsat 7 ETM+ sensor imagery, were used as discriminating variables. The two classifiers were trained and validated for each soil class using 300 and 150 samples respectively, representing the characteristics of these classes in terms of the discriminating variables. According to the statistical tests, the accuracy of the classifier based on artificial neural networks (ANNs) was greater than of the classic Maximum Likelihood Classifier (MLC). Comparing the results with 126 points of reference showed that the resulting ANN map (73.81 %) was superior to the MLC map (57.94 %). The main errors when using the two classifiers were caused by: a) the geological heterogeneity of the area coupled with problems related to the geological map; b) the depth of lithic contact and/or rock exposure, and c) problems with the environmental correlation model used due to the polygenetic nature of the soils. This study confirms that the use of terrain attributes together with remote sensing data by an ANN approach can be a tool to facilitate soil mapping in Brazil, primarily due to the availability of low-cost remote sensing data and the ease by which terrain attributes can be obtained.

A linkage map of spring turnip rape based on RFLP and RAPD markers

Selostus: RAPD- ja RFLP-markkereista koostuva rypsin kytkentäkartta

Processes models, environmental analyses, and cognitive architectures: Quo vadis quantum probability theory? (Commentary on Pothos and Busemeyer)

A lot of research in cognition and decision making suffers from a lack of formalism. The quantum probability program could help to improve this situation, but we wonder whether it would provide even more added value if its presumed focus on outcome models were complemented by process models that are, ideally, informed by ecological analyses and integrated into cognitive architectures.

Auditory perceptual decision-making based on semantic categorization of environmental sounds.

Discriminating complex sounds relies on multiple stages of differential brain activity. The specific roles of these stages and their links to perception were the focus of the present study. We presented 250ms duration sounds of living and man-made objects while recording 160-channel electroencephalography (EEG). Subjects categorized each sound as that of a living, man-made or unknown item. We tested whether/when the brain discriminates between sound categories even when not transpiring behaviorally. We applied a single-trial classifier that identified voltage topographies and latencies at which brain responses are most discriminative. For sounds that the subjects could not categorize, we could successfully decode the semantic category based on differences in voltage topographies during the 116-174ms post-stimulus period. Sounds that were correctly categorized as that of a living or man-made item by the same subjects exhibited two periods of differences in voltage topographies at the single-trial level. Subjects exhibited differential activity before the sound ended (starting at 112ms) and on a separate period at ~270ms post-stimulus onset. Because each of these periods could be used to reliably decode semantic categories, we interpreted the first as being related to an implicit tuning for sound representations and the second as being linked to perceptual decision-making processes. Collectively, our results show that the brain discriminates environmental sounds during early stages and independently of behavioral proficiency and that explicit sound categorization requires a subsequent processing stage.

Origin-related, environmental, sex, and age determinants of immunocompetence, susceptibility to ectoparasites, and disease symptoms in the barn owl

Knowledge of the role of origin-related, environmental, sex, and age factors on host defence mechanisms is important to understand variation in parasite intensity. Because alternative components of parasite defence may be differently sensitive to various factors, they may not necessarily covary. Many components should therefore be considered to tackle the evolution of host-parasite interactions. In a population of barn owls (Tyto alba), we investigated the role of origin-related, environmental (i.e. year, season, nest of rearing, and body condition), sex, and age factors on 12 traits linked to immune responses [humoral immune responses towards sheep red blood cells (SRBC), human serum albumin (HSA) and toxoid toxin TT, T-cell mediated immune response towards the mitogen phytohemagglutinin (PHA)], susceptibility to ectoparasites (number and fecundity of Carnus haemapterus, number of Ixodes ricinus), and disease symptoms (size of the bursa of Fabricius and spleen, proportion of proteins that are immunoglobulins, haematocrit and blood concentration in leucocytes). Cross-fostering experiments allowed us to detect a heritable component of variation in only four out of nine immune and parasitic parameters (i.e. SRBC- and HSA-responses, haematocrit, and number of C. haemapterus). However, because nestlings were not always cross-fostered just after hatching, the finding that 44% of the immune and parasitic parameters were heritable is probably an overestimation. These experiments also showed that five out of these nine parameters were sensitive to the nest environment (i.e. SRBC- and PHA-responses, number of C. haemapterus, haematocrit and blood concentration in leucocytes). Female nestlings were more infested by the blood-sucking fly C. haemapterus than their male nestmates, and their blood was less concentrated in leucocytes. The effect of year, season, age (i.e. reflecting the degree of maturation of the immune system), brood size, position in the within-brood age hierarchy, and body mass strongly differed between the 12 parameters. Different components of host defence mechanisms are therefore not equally heritable and sensitive to environmental, sex, and age factors, potentially explaining why most of these components did not covary.

Forest insects and environmental variation in stand edges

Summary

Plant species distributions along environmental gradients: do belowground interactions with fungi matter?

The distribution of plants along environmental gradients is constrained by abiotic and biotic factors. Cumulative evidence attests of the impact of biotic factors on plant distributions, but only few studies discuss the role of belowground communities. Soil fungi, in particular, are thought to play an important role in how plant species assemble locally into communities. We first review existing evidence, and then test the effect of the number of soil fungal operational taxonomic units (OTUs) on plant species distributions using a recently collected dataset of plant and metagenomic information on soil fungi in the Western Swiss Alps. Using species distribution models (SDMs), we investigated whether the distribution of individual plant species is correlated to the number of OTUs of two important soil fungal classes known to interact with plants: the Glomeromycetes, that are obligatory symbionts of plants, and the Agaricomycetes, that may be facultative plant symbionts, pathogens, or wood decayers. We show that including the fungal richness information in the models of plant species distributions improves predictive accuracy. Number of fungal OTUs is especially correlated to the distribution of high elevation plant species. We suggest that high elevation soil show greater variation in fungal assemblages that may in turn impact plant turnover among communities. We finally discuss how to move beyond correlative analyses, through the design of field experiments manipulating plant and fungal communities along environmental gradients.

Vehicular Traffic Flow Map, 1988

Traffic volumes represented on this map are annual average daily traffic volumes between major traffic generators: highway junctions and cities.

Vehicular Traffic Flow Map, 1990

Traffic volumes represented on this map are annual average daily traffic volumes between major traffic generators: highway junctions and cities.

Vehicular Traffic Flow Map, 1992

Traffic volumes represented on this map are annual average daily traffic volumes between major traffic generators: highway junctions and cities.