Environmental data mining and modeling based on machine learning algorithms and geostatistics

The paper presents some contemporary approaches to spatial environmental data analysis. The main topics are concentrated on the decision-oriented problems of environmental spatial data mining and modeling: valorization and representativity of data with the help of exploratory data analysis, spatial predictions, probabilistic and risk mapping, development and application of conditional stochastic simulation models. The innovative part of the paper presents integrated/hybrid model-machine learning (ML) residuals sequential simulations-MLRSS. The models are based on multilayer perceptron and support vector regression ML algorithms used for modeling long-range spatial trends and sequential simulations of the residuals. NIL algorithms deliver non-linear solution for the spatial non-stationary problems, which are difficult for geostatistical approach. Geostatistical tools (variography) are used to characterize performance of ML algorithms, by analyzing quality and quantity of the spatially structured information extracted from data with ML algorithms. Sequential simulations provide efficient assessment of uncertainty and spatial variability. Case study from the Chernobyl fallouts illustrates the performance of the proposed model. It is shown that probability mapping, provided by the combination of ML data driven and geostatistical model based approaches, can be efficiently used in decision-making process. (C) 2003 Elsevier Ltd. All rights reserved.

Magmatic fluids in the Breccia-hosted epithermal Au-Ag deposit of Rosia Montana, Romania

The breccia-hosted epithermal Au-Ag deposit of Rosia Montana is located 7 kin northeast of Abrud, in the northern part of the South Apuseni Mountains, Romania. Estimated total reserves of 214.91 million metric toils (Mt) of ore at 1.46 g/t An and 6.9 g/t Ag (10.1 Moz of An and 47.6 Moz of Ag) make Rosia Montana one of the largest gold deposits in Europe. At this location, Miocene calc-alkaline magmatic and hydrothermal activity was associated with local extensional tectonics within a strike-slip regime related to the indentation of the Adriatic microplate into the European plate during the Carpathian orogenesis. The host rocks of the magmatic complex consist of pre-Mesozoic metamorphosed continental crust covered by Cretaceous turbiditic sediment (flysch). Magmatic activity at Rosia Montana and its surroundings occurred in several pulses and lasted about 7 m.y, Rosia Montana is a breccia-hosted epithermal system related to strong phreatomagmatic activity due to the shallow emplacement of the Montana dacite. The Montana dacite intruded Miocene volcaniclastic material (volcaniclastic breccias) and crops out at Cetate and Carnic Hills. Current mining is focused primarily on the Cetate open pit, which was mapped in detail, leading to the recognition of three distinct breccia bodies: the dacite breccia with a dominantly hydrothermal matrix, the gray polymict breccia with a greater proportion of sand-sized matrix support, and the black polymict breccia, which reached to the surface, contains carbonized tree trunks and has a dominantly barren elastic matrix. The hydrothermal alteration is pervasive. Adularia alteration with a phyllic overprint is ubiquitous; silicification and argillic alteration occur locally. Mineralization consists of quartz, adularia, carbonates (commonly Mn-rich), pyrite, Fe-poor sphalerite, galena, chalcopyrite, tetrahedrite, and native gold and occurs as disseminations, as well as in veins and filling vugs within the Montana dacite and the different breccias. The age of mineralization (12.85 +/- 0.07 Ma) was determined by Ar-40- Ar-39 dating on hydrothermal adularia crystals from vugs in the dacite breccia in the Cetate open pit. Microthermometric measurements of fluid inclusions in quartz phenocrysts from the Montana dacite revealed two fluid types that are absent from the hydrothermal breccia and must have been trapped at depth prior to dacite dome emplacement: brine inclusions (32-55 -wt % NaCl equiv, homogenizing at T-h > 460 degrees C) and intermediate density fluids (4.9-15.6 wt % NaCl equiv, T, between 345 degrees-430 degrees C). Secondary aqueous fluid inclusion assemblages in the phenocrysts have salinities of 0.2 to 2.2 wt percent NaCl equiv and T-h of 200 degrees to 280 degrees C. Fluid inclusion assemblages in hydrothermal quartz from breccias and veins have salinities of 0.2 to 3.4 wt percent NaCl equiv and T-h, from 200 degrees to 270 degrees C. The oxygen isotope composition of several zones of an ore-related epithermal quartz crystal indicate a very constant delta O-18 of 4.5 to 5.0 per mil for the mineralizing fluid, despite significant salinity and temperature variation over time. Following microthermometry, selected fluid inclusion assemblages were analyzed by laser ablation-inductively coupled-plasma mass spectrometry (LA-ICMS). Despite systematic differences in salinity between phenocryst-hosted fluids trapped at depth and fluids from quartz in the epithermal breccias, all fluids have overlapping major and trace cation ratios, including identical Na/K/Rb/Sr/Cs/Ba. Consistent with the constant near-magmatic oxygen isotope composition of the hydrothermal fluids, these data strongly indicate a common magmatic component of these chemically conservative solutes in all fluids. Cu, Pb, Zn, and Mn show variations in concentration relative to the relatively non-reactive alkalis, reflecting the precipitation of sulfide minerals together with An in the epithermal breccia, and possibly of Cu in an inferred subjacent porphyry environment. The magmatic-hydrothermal processes responsible for epithermal Au-Ag mineralization at Rosia Montana are, however, not directly related to the formation of the spatially associated porphyry Cu-Au deposit of Rosia Poieni, which occurred lout 3 m.y. later.

Multi-scale support vector algorithms for hot spot detection and modelling

The algorithmic approach to data modelling has developed rapidly these last years, in particular methods based on data mining and machine learning have been used in a growing number of applications. These methods follow a data-driven methodology, aiming at providing the best possible generalization and predictive abilities instead of concentrating on the properties of the data model. One of the most successful groups of such methods is known as Support Vector algorithms. Following the fruitful developments in applying Support Vector algorithms to spatial data, this paper introduces a new extension of the traditional support vector regression (SVR) algorithm. This extension allows for the simultaneous modelling of environmental data at several spatial scales. The joint influence of environmental processes presenting different patterns at different scales is here learned automatically from data, providing the optimum mixture of short and large-scale models. The method is adaptive to the spatial scale of the data. With this advantage, it can provide efficient means to model local anomalies that may typically arise in situations at an early phase of an environmental emergency. However, the proposed approach still requires some prior knowledge on the possible existence of such short-scale patterns. This is a possible limitation of the method for its implementation in early warning systems. The purpose of this paper is to present the multi-scale SVR model and to illustrate its use with an application to the mapping of Cs137 activity given the measurements taken in the region of Briansk following the Chernobyl accident.

Analyse comparée de régimes institutionnels de gestion des réseaux urbains de l'eau en station touristique de montagne : les cas de Crans-Montana (Suisse) et de Morzine-Avoriaz (France)

La station touristique représente un espace urbain consacré principalement au tourisme, tout en comprenant également une population résidente permanente. Du point de vue de la gestion des réseaux urbains de l'eau, cette caractéristique induit pour ce type de lieu des usages propres à tout espace urbain mais également des spécificités liées à la forte fluctuation saisonnière de la population résidente ou encore à la présence d'usages particuliers tels que l'irrigation des golfs, la production de neige artificielle ou le thermalisme. Dès lors, la planification de l'approvisionnement est délicate et peu prévisible. Ces difficultés sont renforcées par le fait que les concentrations temporelles de la demande coïncident généralement avec des périodes de stress hydrique notable. Dans le cas de stations balnéaires, les pics de fréquentation interviennent en général durant l'été lorsque la ressource en eau est peu disponible. Le problème est similaire dans les stations touristiques de montagne où l'eau est généralement indisponible car stockée sous forme de neige durant les mois de forte fréquentation. De plus, ces difficultés sont souvent renforcées par la localisation géographique des stations touristiques, fréquemment situées dans des espaces sensibles du point de vue de la ressource en eau, avec des situations de pénuries temporelles, voire structurelles. Ces problématiques propres à la plupart des stations touristiques mènent souvent à de fortes rivalités entre, d'une part, les différents usages touristiques de la ressource, et d'autre part, les usages autochtones et touristiques. Les particularités liées au tourisme tendent ainsi à renforcer les rivalités entre différents types de secteurs d'activité (approvisionnement en eau potable, tourisme, hydroélectricité, enneigement artificiel, irrigation, etc.). Ces différents usages de la ressource mis en concurrence nécessitent dès lors la mise en oeuvre de réglementations structurées à travers des politiques publiques ainsi que des droits de propriété et selon des composantes nationales, régionales et locales ; soit un cadre institutionnel que nous proposons d'appeler Régime Institutionnel de Ressource (RIR) (Knoepfel et al. 2001, 2007). A travers cette thèse de doctorat, nous répondons à différentes questions de recherche. Nous tentons d'abord de comprendre comment ces différents RIR sont-ils mis en oeuvre dans le cadre d'espaces touristiques ? Comment ceux-ci sont-ils concrétisés par les acteurs et quels sont leurs effets en termes de durabilité technique, environnementale, sociale et économique des réseaux urbains de l'eau ? Nous questionnons ensuite les effets du tourisme sur la gestion des infrastructures de réseau à l'échelle de la station touristique et de son bassin versant et nous interrogeons sur les effets du tourisme en termes de gestion des eaux urbaines. Nous portons notre attention sur deux stations touristiques situées dans deux contextes institutionnels différents (Crans-Montana en Suisse et Morzine-Avoriaz en France) et y étudions trois types de régimes institutionnels en particulier : la régie directe (gestion publique), l'affermage (gestion déléguée) et la gestion privée des infrastructures. Les résultats de cette thèse de doctorat indiquent tout d'abord dans quelle mesure le tourisme modifie de façon significative la perception et les modalités de gestion de la ressource en eau et des infrastructures. Ils montrent ensuite que l'espace fonctionnel de la gestion de ces infrastructures correspond rarement aux limites du réseau hydrographique naturel et quelles en sont les implications en termes de durabilité. Enfin, la comparaison de différents régimes institutionnels révèle les forces et les faiblesses de chaque modèle de gestion dans le cas spécifique des stations touristiques et également les différentes solutions adoptées localement pour la mise en oeuvre d'un arrangement institutionnel permettant un usage plus ou moins durable des infrastructures de réseau et du réseau hydrographique naturel. - Tourism resort represents an urban area mainly dedicated to tourism while including at the same time a permanent residential population. From the point of view of urban water networks, this characteristic induces a strong seasonal fluctuation of residential population and involves special water uses such as golf irrigation, production of artificial snow or functioning of thermal baths. Therefore, water supply planning can be tricky and difficult to predict. These difficulties are reinforced by the fact that temporary concentrations of water demand coïncidé generally with periods of water stress. In the case of seaside resorts, frequenting peaks arise in general during summer when water resource is less available. The problem is similar in mountainous tourist resorts where water is generally unavailable as it is stored as snow during months of highest frequenting. Furthermore, these difficulties are often reinforced by resorts' geographical localisations, which are often situated in sensitive areas in terms of temporary or structural water shortages. These problematic issues often lead to strong rivalries between tourists' water uses on the one hand, and between locals and tourists uses on the other hand. Thus, features of tourism tend to reinforce rivalries between different sectors of activity (supply of drinking water, tourism, hydroelectricity, artificial snow, irrigation, etc.). These different and competing water uses need the implementation of rules structured through public policies and property rights and through national, regional and local legal components; We propose to call this framework as an Institutional Resource Regime (IRR) (Knoepfel et al. 2001, 2007, 2009). Through this PhD thesis, we answer different research questions. We firstly aim to understand how those different IRR are implemented within tourism spaces? How do actors materialize them and what are their effects in term of technical, environmental, social and economical sustainability of urban water networks? We then, investigate effects of tourism on water networks infrastructures' management at the scale of the tourist resort and its river basin. We focus our attention on two tourist resorts situated within two different institutional contexts (Crans-Montana, Switzerland and Morzine-Avoriaz, France) and study three types of institutional regime in particular: public, delegated and private management of infrastructures. Results of this PhD thesis indicate firstly how tourism modifies in a significant way the perception and management modalities of water resource and infrastructures. Results also show that functional space of infrastructures management rarely matches with the limits of the natural river basin and indicates what it means in terms of sustainability. Finally, the comparison of different institutional regimes reveals the strengths and weakness of each management model in the specific case of tourist resorts and shows the different solutions in locally implementing an institutional arrangement for a more or less sustainable management of network infrastructures and natural water system.

Current approaches and challenges for the metabolite profiling of complex natural extracts.

Metabolite profiling is critical in many aspects of the life sciences, particularly natural product research. Obtaining precise information on the chemical composition of complex natural extracts (metabolomes) that are primarily obtained from plants or microorganisms is a challenging task that requires sophisticated, advanced analytical methods. In this respect, significant advances in hyphenated chromatographic techniques (LC-MS, GC-MS and LC-NMR in particular), as well as data mining and processing methods, have occurred over the last decade. Together, these tools, in combination with bioassay profiling methods, serve an important role in metabolomics for the purposes of both peak annotation and dereplication in natural product research. In this review, a survey of the techniques that are used for generic and comprehensive profiling of secondary metabolites in natural extracts is provided. The various approaches (chromatographic methods: LC-MS, GC-MS, and LC-NMR and direct spectroscopic methods: NMR and DIMS) are discussed with respect to their resolution and sensitivity for extract profiling. In addition the structural information that can be generated through these techniques or in combination, is compared in relation to the identification of metabolites in complex mixtures. Analytical strategies with applications to natural extracts and novel methods that have strong potential, regardless of how often they are used, are discussed with respect to their potential applications and future trends.

Integration of genome-wide association studies with biological knowledge identifies six novel genes related to kidney function.

In conducting genome-wide association studies (GWAS), analytical approaches leveraging biological information may further understanding of the pathophysiology of clinical traits. To discover novel associations with estimated glomerular filtration rate (eGFR), a measure of kidney function, we developed a strategy for integrating prior biological knowledge into the existing GWAS data for eGFR from the CKDGen Consortium. Our strategy focuses on single nucleotide polymorphism (SNPs) in genes that are connected by functional evidence, determined by literature mining and gene ontology (GO) hierarchies, to genes near previously validated eGFR associations. It then requires association thresholds consistent with multiple testing, and finally evaluates novel candidates by independent replication. Among the samples of European ancestry, we identified a genome-wide significant SNP in FBXL20 (P = 5.6 × 10(-9)) in meta-analysis of all available data, and additional SNPs at the INHBC, LRP2, PLEKHA1, SLC3A2 and SLC7A6 genes meeting multiple-testing corrected significance for replication and overall P-values of 4.5 × 10(-4)-2.2 × 10(-7). Neither the novel PLEKHA1 nor FBXL20 associations, both further supported by association with eGFR among African Americans and with transcript abundance, would have been implicated by eGFR candidate gene approaches. LRP2, encoding the megalin receptor, was identified through connection with the previously known eGFR gene DAB2 and extends understanding of the megalin system in kidney function. These findings highlight integration of existing genome-wide association data with independent biological knowledge to uncover novel candidate eGFR associations, including candidates lacking known connections to kidney-specific pathways. The strategy may also be applicable to other clinical phenotypes, although more testing will be needed to assess its potential for discovery in general.