Advanced mapping of environmental data: Geostatistics, Machine Learning and Bayesian Maximum Entropy

This book combines geostatistics and global mapping systems to present an up-to-the-minute study of environmental data. Featuring numerous case studies, the reference covers model dependent (geostatistics) and data driven (machine learning algorithms) analysis techniques such as risk mapping, conditional stochastic simulations, descriptions of spatial uncertainty and variability, artificial neural networks (ANN) for spatial data, Bayesian maximum entropy (BME), and more.

Extreme Precipitation Modelling Using Geostatistics and Machine Learning Algorithms

The paper presents an approach for mapping of precipitation data. The main goal is to perform spatial predictions and simulations of precipitation fields using geostatistical methods (ordinary kriging, kriging with external drift) as well as machine learning algorithms (neural networks). More practically, the objective is to reproduce simultaneously both the spatial patterns and the extreme values. This objective is best reached by models integrating geostatistics and machine learning algorithms. To demonstrate how such models work, two case studies have been considered: first, a 2-day accumulation of heavy precipitation and second, a 6-day accumulation of extreme orographic precipitation. The first example is used to compare the performance of two optimization algorithms (conjugate gradients and Levenberg-Marquardt) of a neural network for the reproduction of extreme values. Hybrid models, which combine geostatistical and machine learning algorithms, are also treated in this context. The second dataset is used to analyze the contribution of radar Doppler imagery when used as external drift or as input in the models (kriging with external drift and neural networks). Model assessment is carried out by comparing independent validation errors as well as analyzing data patterns.

From the vendor in the hemp shop to the dealer in the alleyway? A comparison of the sources of supply of cannabis in a time of 'de-normalising' cannabis use.

Objectives: After several years of increasing 'normalisation' of cannabis use in Switzerland at the beginning of the new millennium, a reversed tendency, marked among others by a more stringent law-enforcement, set in. The presentation examines the question of where adolescents and young adults obtained cannabis, within the context of this societal change. In addition, it compares the sources of supply for cannabis with those found in studies of other European countries. Methods: Analyses are based on data from the Swiss Cannabis Monitoring Study. As part of this longitudinal, representative population survey, more than 5000 adolescents and young adults were interviewed by telephone on the topic of cannabis. Within the total sample, 593 (2004) or 554 (2007) respectively, current cannabis users replied to the questions on sources of supply. Changes in law-enforcement and societal climate concerning cannabis are assessed based on relevant literature, media reports and parliamentary discussions. Results: Whereas 22% of cannabis users stated in 2004 that they bought their cannabis from vendors in hemp shops, this proportion drastically decreased to 6% three years later. At the same time, cannabis was obtained increasingly from friends, while the proportion of users who purchased cannabis from dealers in the alleyway, more than doubled from 6% (2004) to 13% (2007). It was male cannabis users, and in particular, young adult and frequent users, who have moved into the alleyways. Generally, users who buy cannabis in the alleyway show more cannabis-related problems than those who mainly name other sources of supply, even when adjusted for sex, age and frequency of cannabis use. Discussion: Possible consequences of these changes in cannabis supply, like the risk of merging a previously cannabis-only market with other 'harder' drugs markets, are discussed.

Cinéma, machine à mondes : essai sur les films à univers multiples

Dans cet ouvrage, l'auteur propose une conceptualisation théorique de la coprésence en un même film de mondes multiples en abordant différents paramètres (hétérogénéité de la facture de l'image, pratiques du montage alterné, typologie des enchâssements, expansion sérielle, etc.) sur la base d'un corpus de films de fiction récents qui appartiennent pour la plupart au genre de la science-fiction (Matrix, Dark City, Avalon, Resident Evil, Avatar,...). Issue de la filmologie, la notion de « diégèse » y est développée à la fois dans le potentiel d'autonomisation dont témoigne la conception mondaine qui semble dominer aujourd'hui à l'ère des jeux vidéo, dans ses liens avec le récit et dans une perspective intermédiale. Les films discutés ont la particularité de mettre en scène des machines permettant aux personnages de passer d'un monde à l'autre : les modes de figuration de ces technologies sont investigués en lien avec les imaginaires du dispositif cinématographique et les potentialité du montage. La comparaison entre les films (Tron et son récent sequel, Totall Recall et son remake) et entre des oeuvres filmiques et littéraires (en particulier les nouvelles de Philip K. Dick et Simlacron 3 de Galouye) constitue un outil d'analyse permettant de saisir la contemporanéité de cette problématique, envisagée sur le plan esthétique dans le contexte de l'imagerie numérique.

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.