Machine learning algorithms for spatial data. Case studies: Environmental pollution, natural hazards, renewable resources

This paper presents general problems and approaches for the spatial data analysis using machine learning algorithms. Machine learning is a very powerful approach to adaptive data analysis, modelling and visualisation. The key feature of the machine learning algorithms is that they learn from empirical data and can be used in cases when the modelled environmental phenomena are hidden, nonlinear, noisy and highly variable in space and in time. Most of the machines learning algorithms are universal and adaptive modelling tools developed to solve basic problems of learning from data: classification/pattern recognition, regression/mapping and probability density modelling. In the present report some of the widely used machine learning algorithms, namely artificial neural networks (ANN) of different architectures and Support Vector Machines (SVM), are adapted to the problems of the analysis and modelling of geo-spatial data. Machine learning algorithms have an important advantage over traditional models of spatial statistics when problems are considered in a high dimensional geo-feature spaces, when the dimension of space exceeds 5. Such features are usually generated, for example, from digital elevation models, remote sensing images, etc. An important extension of models concerns considering of real space constrains like geomorphology, networks, and other natural structures. Recent developments in semi-supervised learning can improve modelling of environmental phenomena taking into account on geo-manifolds. An important part of the study deals with the analysis of relevant variables and models' inputs. This problem is approached by using different feature selection/feature extraction nonlinear tools. To demonstrate the application of machine learning algorithms several interesting case studies are considered: digital soil mapping using SVM, automatic mapping of soil and water system pollution using ANN; natural hazards risk analysis (avalanches, landslides), assessments of renewable resources (wind fields) with SVM and ANN models, etc. The dimensionality of spaces considered varies from 2 to more than 30. Figures 1, 2, 3 demonstrate some results of the studies and their outputs. Finally, the results of environmental mapping are discussed and compared with traditional models of geostatistics.

The politics of contaminated sites management : institutional regime change and actor's mode of participation in the environmental management of the Bonfol Chemical Waste Landfill in Switzerland

By the end of the 1970s, contaminated sites had emerged as one of the most complex and urgent environmental issues affecting industrialized countries. The authors show that small and prosperous Switzerland is no exception to the pervasive problem of sites contamination, the legacy of past practices in waste management having left some 38,000 contaminated sites throughout the country. This book outlines the problem, offering evidence that open and polycentric environmental decision-making that includes civil society actors is valuable. They propose an understanding of environmental management of contaminated sites as a political process in which institutions frame interactions between strategic actors pursuing sometimes conflicting interests. In the opening chapter, the authors describe the influences of politics and the power relationships between actors involved in decision-making in contaminated sites management, which they term a "wicked problem." Chapter Two offers a theoretical framework for understanding institutions and the environmental management of contaminated sites. The next five chapters present a detailed case study on environmental management and contaminated sites in Switzerland, focused on the Bonfol Chemical Landfill. The study and analysis covers the establishment of the landfill under the first generation of environmental regulations, its closure and early remediation efforts, and the gambling on the remediation objectives, methods and funding in the first decade of the 21st Century. The concluding chapter discusses the question of whether the strength of environmental regulations, and the type of interactions between public, private, and civil society actors can explain the environmental choices in contaminated sites management. Drawing lessons from research, the authors debate the value of institutional flexibility for dealing with environmental issues such as contaminated sites.

Will climate change drive alien invasive plants into areas of high protection value? An improved model-based regional assessment to prioritise the management of invasions.

Species distribution models (SDMs) studies suggest that, without control measures, the distribution of many alien invasive plant species (AIS) will increase under climate and land-use changes. Due to limited resources and large areas colonised by invaders, management and monitoring resources must be prioritised. Choices depend on the conservation value of the invaded areas and can be guided by SDM predictions. Here, we use a hierarchical SDM framework, complemented by connectivity analysis of AIS distributions, to evaluate current and future conflicts between AIS and high conservation value areas. We illustrate the framework with three Australian wattle (Acacia) species and patterns of conservation value in Northern Portugal. Results show that protected areas will likely suffer higher pressure from all three Acacia species under future climatic conditions. Due to this higher predicted conflict in protected areas, management might be prioritised for Acacia dealbata and Acacia melanoxylon. Connectivity of AIS suitable areas inside protected areas is currently lower than across the full study area, but this would change under future environmental conditions. Coupled SDM and connectivity analysis can support resource prioritisation for anticipation and monitoring of AIS impacts. However, further tests of this framework over a wide range of regions and organisms are still required before wide application.

Generalized linear and generalized additive models in studies of species distributions: setting the scene

An important statistical development of the last 30 years has been the advance in regression analysis provided by generalized linear models (GLMs) and generalized additive models (GAMs). Here we introduce a series of papers prepared within the framework of an international workshop entitled: Advances in GLMs/GAMs modeling: from species distribution to environmental management, held in Riederalp, Switzerland, 6-11 August 2001.We first discuss some general uses of statistical models in ecology, as well as provide a short review of several key examples of the use of GLMs and GAMs in ecological modeling efforts. We next present an overview of GLMs and GAMs, and discuss some of their related statistics used for predictor selection, model diagnostics, and evaluation. Included is a discussion of several new approaches applicable to GLMs and GAMs, such as ridge regression, an alternative to stepwise selection of predictors, and methods for the identification of interactions by a combined use of regression trees and several other approaches. We close with an overview of the papers and how we feel they advance our understanding of their application to ecological modeling.

Compendium of projects in the European nanosafety cluster

The demand for research in the area of safety health and environmental management of nanotechnologies is present since a decade and identified by several landmark reports and studies. It is not the intention of this compendium to report on these as they are widely available. It is also not the intention to publish scientific papers and research results as this task is covered by scientific conferences and the peer reviewed press. The intention of the compendium is to bring together researchers, create synergy in their work, and establish links and communication between them mainly during the actual research phase before publication of results. Towards this purpose we find useful to give emphasis to communication of projects strategic aims, extensive coverage of specific work objectives and of methods used in research, strengthening human capacities and laboratories infrastructure, supporting collaboration for common goals and joint elaboration of future plans, without compromising scientific publication potential or IP Rights. These targets are far from being achieved with the publication in its present shape. We shall continue working, though, and hope with the assistance of the research community to make significant progress. We would like to stress that this sector is under development and progressing very fast, which might make some of the statements outdated or even obsolete. Nevertheless it is intended to provide a basis for the necessary future developments. [Ed.]

Blood pressure treatment in acute ischemic stroke: a review of studies and recommendations.

PURPOSE OF REVIEW: Elevated blood pressure (BP) is frequent in patients with acute ischemic stroke. Pathophysiological data support its usefulness to maintain adequate perfusion of the ischemic penumba. This review article aims to summarize the available evidence from clinical studies that examined the prognostic role of BP during the acute phase of ischemic stroke and intervention studies that assessed the efficacy of active BP alteration. RECENT FINDINGS: We found 34 observational studies (33,470 patients), with results being inconsistent among the studies; most studies reported a negative association between increased levels of BP and clinical outcome, whereas a few studies showed clinical improvement with higher BP levels, clinical deterioration with decreased BP, or no association at all. Similarly, the conclusions drawn by the 18 intervention studies included in this review (1637 patients) were also heterogeneous. Very recent clinical data suggest a possible beneficial effect of early treatment with some antihypertensives on late clinical outcome. SUMMARY: Observational and interventional studies of management of acute poststroke hypertension yield conflicting results. We discuss different explanations that may account for this and discuss the current guidelines and pathophysiological considerations for the management of acute poststroke hypertension.

Ecology and evolution of multigenomic arbuscular mycorrhizal fungi.

Arbuscular mycorrhizal fungi (AMF) form extremely important mutualistic symbioses with most plants. Their role in nutrient acquisition, plant community structure, plant diversity, and ecosystem productivity and function has been demonstrated in recent years. New findings on the genetics and biology of AMF also give us a new picture of how these fungi exist in ecosystems. In this article, I bring together some recent findings that indicate that AMF have evolved to contain multiple genomes, that they connect plants together by a hyphal network, and that these different genomes may potentially move around in this network. These findings show the need for more intensive studies on AMF population biology and genetics in order to understand how they have evolved with plants, to better understand their ecological role, and for applying AMF in environmental management programs and in agriculture. A number of key features of AMF population biology have been identified for future studies and most of these concern the need to understand drift, selection, and genetic exchange in multigenomic organisms, a task that has not previously presented itself to evolutionary biologists.

Comparison of potential adjustment variables representing primary intellectual level in epidemiological studies on neurotoxicity

BACKGROUND: Primary intellectual abilities (PIA) are a confounder in epidemiological studies on neurotoxicity. A good measure of this confounder should be independent of age as PIA is an intrinsic ability. Furthermore, as PIA is related to health endpoints, any measure of PIA should reveal this association. This study is aimed at comparing vocabulary test, diploma and age at end of schooling properties as measures of PIA in a non-exposed population of workers. METHODS: The design was a cross-sectional study of 413 non-exposed workers (203 women and 210 men) selected from a health check-up center. The effect of age on the vocabulary score was assessed using an analysis of covariance adjusted for diploma. Relationships between neuropsychological performances and vocabulary score, diploma and end of schooling age were, respectively, assessed using multiple linear regressions adjusted for age and gender. RESULTS: Vocabulary score increased significantly with age, both for men and women. The increase was 0.14 word per year for women, and 0.18 word per year for men. The explained variance of the models evaluating the relationships between age at end of schooling, diploma, vocabulary test, and neuropsychological performances was quite similar for the three measures of PIA. CONCLUSIONS: Vocabulary score was found to be age-related, even after adjustment for diploma. No difference was found between these three variables in terms of their relationship to neuropsychological endpoints. Moreover, the literature shows that vocabulary test performances are influenced by exposure to neurotoxic agents. These results suggest that vocabulary score could be of interest for participants of similar ages and similar diplomas. Otherwise, the other two variables would be better PIA measures in neurotoxicology studies.

Management Control for Corporate Sustainability Execution: The Role of Employee Compensation

The research described in this thesis examines the characteristics, the benefits and the challenges associated with the implementation of management accounting systems in the field of Corporate Social Responsibility (CSR). Applied to the CSR context, management accounting relates to the identification, elaboration and communication of information about an organization's interactions with the society and the environment. Based on this information, firms are able to make decisions to achieve social and environmental objectives and provide evidence justifying the benefits and the costs of such actions. The study begins by focusing on green management and exploring the characteristics of Environmental Management Accounting (EMA) systems within firms. The first chapter informs the reader about the growing body of EMA research and reveals unexplored relevant aspects that need to be further investigated. The work also emphasizes the importance of developing new theoretical hypotheses and appropriate research designs to empirically tackle new aspects of EMA and gain understanding on the use of these practices. Subsequently, given the acknowledged importance of control systems in influencing the behaviour of individuals within organizations, the remaining two chapters of the dissertation focus on the functioning of CSR-linked incentives assigned to employees in the form of compensation plans. The second chapter examines the determinants influencing corporate provision of incentives for the attainment of environmental targets. Empirical analysis of a sample of international firms reveals that companies are likely to use green incentives as mechanisms to increase the efficacy in contracting with their employees as well as to respond to social influences. Finally, the third chapter investigates the effectiveness of contracting associated with the use of CSR-linked executive compensation. Empirical analysis of a sample of US-based companies shows that corporate choice to tie senior executives' pay to CSR targets promotes the firm's CSR performance. Cette thèse examine les caractéristiques, avantages et défis associés à l'utilisation des systèmes de contrôle de gestion dans le domaine de la Responsabilité Sociale des Entreprises (RSE). Dans le contexte de la RSE, les activités du contrôle de gestion impliquent l'identification, l'élaboration et la communication d'informations qui concernent les interactions des organisations avec la société et l'environnement. Avec ces informations les entreprises sont en mesure de prendre des décisions visant à atteindre les objectifs sociaux et environnementaux de l'organisation et de documenter les bénéfices et coûts de ces actions. Dès le début, la thèse se concentre sur les caractéristiques des systèmes de contrôle de gestion environnementale au sein des entreprises. Le premier chapitre passe en revue la littérature existante et révèle des aspects inexplorés. Pour ce faire, le travail suggère le développement de nouvelles théories ainsi que l'utilisation de méthodes appropriées. Ces dernières doivent permettre d'aborder empiriquement de nouveaux aspects des systèmes de contrôle environnemental et faciliter la compréhension sur l'utilisation de ces pratiques. Considérant l'importance des systèmes de contrôle pour influencer le comportement des individus au sein des organisations, la suite du travail se concentre sur le fonctionnement des contrats de rémunération des employées liées aux résultats de la RSE. Plus particulièrement, le deuxième chapitre examine les facteurs qui influencent la décision des entreprises d'assigner des objectifs environnementaux aux employées. L'analyse empirique d'un échantillon d'entreprises internationales montre que les entreprises sont susceptibles d'utiliser des mécanismes incitatifs écologiques pour augmenter l'efficacité des contrats ainsi que pour répondre aux influences sociales. Finalement, le troisième chapitre analyse l'efficacité des contrats de rémunération des dirigeants liés aux résultats de la RSE. L'analyse empirique d'un échantillon de sociétés américaines indique que le choix de l'entreprise de lier la rémunération des dirigeants à des objectifs de la RSE favorise la performance RSE de l'organisation.

Variation in Current Management of Term and Late-preterm Neonates at Risk for Early-onset Sepsis: An International Survey and Review of Guidelines.

BACKGROUND: Uncertainty about the presence of infection results in unnecessary and prolonged empiric antibiotic treatment of newborns at risk for early-onset sepsis (EOS). This study evaluates the impact of this uncertainty on the diversity in management. METHODS: A web-based survey with questions addressing management of infection risk-adjusted scenarios was performed in Europe, North America, and Australia. Published national guidelines (n = 5) were reviewed and compared with the results of the survey. RESULTS: 439 Clinicians (68% were neonatologists) from 16 countries completed the survey. In the low-risk scenario, 29% would start antibiotic therapy and 26% would not, both groups without laboratory investigations; 45% would start if laboratory markers were abnormal. In the high-risk scenario, 99% would start antibiotic therapy. In the low-risk scenario, 89% would discontinue antibiotic therapy before 72 hours. In the high-risk scenario, 35% would discontinue therapy before 72 hours, 56% would continue therapy for 5-7 days, and 9% for more than 7 days. Laboratory investigations were used in 31% of scenarios for the decision to start, and in 72% for the decision to discontinue antibiotic treatment. National guidelines differ considerably regarding the decision to start in low-risk and regarding the decision to continue therapy in higher risk situations. CONCLUSIONS: There is a broad diversity of clinical practice in management of EOS and a lack of agreement between current guidelines. The results of the survey reflect the diversity of national guidelines. Prospective studies regarding management of neonates at risk of EOS with safety endpoints are needed.

History matters: relating paths and rates of landscape change to butterfly species decline

Western European landscapes have drastically changed since the 1950s, with agricultural intensifications and the spread of urban settlements considered the most important drivers of this land-use/land-cover change. Losses of habitat for fauna and flora have been a direct consequence of this development. In the present study, we relate butterfly occurrence to land-use/land-cover changes over five decades between 1951 and 2000. The study area covers the entire Swiss territory. The 10 explanatory variables originate from agricultural statistics and censuses. Both state as well as rate was used as explanatory variables. Species distribution data were obtained from natural history collections. We selected eight butterfly species: four species occur on wetlands and four occur on dry grasslands. We used cluster analysis to track land-use/land-cover changes and to group communes based on similar trajectories of change. Generalized linear models were applied to identify factors that were significantly correlated with the persistence or disappearance of butterfly species. Results showed that decreasing agricultural areas and densities of farms with more than 10 ha of cultivated land are significantly related with wetland species decline, and increasing densities of livestock seem to have favored disappearance of dry grassland species. Moreover, we show that species declines are not only dependent on land-use/land-cover states but also on the rates of change; that is, the higher the transformation rate from small to large farms, the higher the loss of dry grassland species. We suggest that more attention should be paid to the rates of landscape change as feasible drivers of species change and derive some management suggestions.

An alternative socio-ecological strategy? International Trade Unions' engagement with climate change

In the context of a global ecological crisis, it is an important move when trade unions turn to environmentalism. Yet, the form that this environmentalism takes is often overlooked. This is especially the case with international trade unions. Based on an empirical study of international trade unions' engagement with the climate change issue, this article argues that international trade unions follow three different (and partially conflicting) strategies. I label these strategies as 'deliberative', 'collaborative growth' and 'socialist', and I examine each in turn. I argue that such analysis is important if we want to identify the potential for transforming the social relations of production that are at the root of the current climate crisis, and for identifying an alternative socio-ecological strategy.