Machine learning for geospatial data : algorithms, software tools and case studies

Résumé Cette thèse est consacrée à l'analyse, la modélisation et la visualisation de données environnementales à référence spatiale à l'aide d'algorithmes d'apprentissage automatique (Machine Learning). L'apprentissage automatique peut être considéré au sens large comme une sous-catégorie de l'intelligence artificielle qui concerne particulièrement le développement de techniques et d'algorithmes permettant à une machine d'apprendre à partir de données. Dans cette thèse, les algorithmes d'apprentissage automatique sont adaptés pour être appliqués à des données environnementales et à la prédiction spatiale. Pourquoi l'apprentissage automatique ? Parce que la majorité des algorithmes d'apprentissage automatiques sont universels, adaptatifs, non-linéaires, robustes et efficaces pour la modélisation. Ils peuvent résoudre des problèmes de classification, de régression et de modélisation de densité de probabilités dans des espaces à haute dimension, composés de variables informatives spatialisées (« géo-features ») en plus des coordonnées géographiques. De plus, ils sont idéaux pour être implémentés en tant qu'outils d'aide à la décision pour des questions environnementales allant de la reconnaissance de pattern à la modélisation et la prédiction en passant par la cartographie automatique. Leur efficacité est comparable au modèles géostatistiques dans l'espace des coordonnées géographiques, mais ils sont indispensables pour des données à hautes dimensions incluant des géo-features. Les algorithmes d'apprentissage automatique les plus importants et les plus populaires sont présentés théoriquement et implémentés sous forme de logiciels pour les sciences environnementales. Les principaux algorithmes décrits sont le Perceptron multicouches (MultiLayer Perceptron, MLP) - l'algorithme le plus connu dans l'intelligence artificielle, le réseau de neurones de régression généralisée (General Regression Neural Networks, GRNN), le réseau de neurones probabiliste (Probabilistic Neural Networks, PNN), les cartes auto-organisées (SelfOrganized Maps, SOM), les modèles à mixture Gaussiennes (Gaussian Mixture Models, GMM), les réseaux à fonctions de base radiales (Radial Basis Functions Networks, RBF) et les réseaux à mixture de densité (Mixture Density Networks, MDN). Cette gamme d'algorithmes permet de couvrir des tâches variées telle que la classification, la régression ou l'estimation de densité de probabilité. L'analyse exploratoire des données (Exploratory Data Analysis, EDA) est le premier pas de toute analyse de données. Dans cette thèse les concepts d'analyse exploratoire de données spatiales (Exploratory Spatial Data Analysis, ESDA) sont traités selon l'approche traditionnelle de la géostatistique avec la variographie expérimentale et selon les principes de l'apprentissage automatique. La variographie expérimentale, qui étudie les relations entre pairs de points, est un outil de base pour l'analyse géostatistique de corrélations spatiales anisotropiques qui permet de détecter la présence de patterns spatiaux descriptible par une statistique. L'approche de l'apprentissage automatique pour l'ESDA est présentée à travers l'application de la méthode des k plus proches voisins qui est très simple et possède d'excellentes qualités d'interprétation et de visualisation. Une part importante de la thèse traite de sujets d'actualité comme la cartographie automatique de données spatiales. Le réseau de neurones de régression généralisée est proposé pour résoudre cette tâche efficacement. Les performances du GRNN sont démontrées par des données de Comparaison d'Interpolation Spatiale (SIC) de 2004 pour lesquelles le GRNN bat significativement toutes les autres méthodes, particulièrement lors de situations d'urgence. La thèse est composée de quatre chapitres : théorie, applications, outils logiciels et des exemples guidés. Une partie importante du travail consiste en une collection de logiciels : Machine Learning Office. Cette collection de logiciels a été développée durant les 15 dernières années et a été utilisée pour l'enseignement de nombreux cours, dont des workshops internationaux en Chine, France, Italie, Irlande et Suisse ainsi que dans des projets de recherche fondamentaux et appliqués. Les cas d'études considérés couvrent un vaste spectre de problèmes géoenvironnementaux réels à basse et haute dimensionnalité, tels que la pollution de l'air, du sol et de l'eau par des produits radioactifs et des métaux lourds, la classification de types de sols et d'unités hydrogéologiques, la cartographie des incertitudes pour l'aide à la décision et l'estimation de risques naturels (glissements de terrain, avalanches). Des outils complémentaires pour l'analyse exploratoire des données et la visualisation ont également été développés en prenant soin de créer une interface conviviale et facile à l'utilisation. Machine Learning for geospatial data: algorithms, software tools and case studies Abstract The thesis is devoted to the analysis, modeling and visualisation of spatial environmental data using machine learning algorithms. In a broad sense machine learning can be considered as a subfield of artificial intelligence. It mainly concerns with the development of techniques and algorithms that allow computers to learn from data. In this thesis machine learning algorithms are adapted to learn from spatial environmental data and to make spatial predictions. Why machine learning? In few words most of machine learning algorithms are universal, adaptive, nonlinear, robust and efficient modeling tools. They can find solutions for the classification, regression, and probability density modeling problems in high-dimensional geo-feature spaces, composed of geographical space and additional relevant spatially referenced features. They are well-suited to be implemented as predictive engines in decision support systems, for the purposes of environmental data mining including pattern recognition, modeling and predictions as well as automatic data mapping. They have competitive efficiency to the geostatistical models in low dimensional geographical spaces but are indispensable in high-dimensional geo-feature spaces. The most important and popular machine learning algorithms and models interesting for geo- and environmental sciences are presented in details: from theoretical description of the concepts to the software implementation. The main algorithms and models considered are the following: multi-layer perceptron (a workhorse of machine learning), general regression neural networks, probabilistic neural networks, self-organising (Kohonen) maps, Gaussian mixture models, radial basis functions networks, mixture density networks. This set of models covers machine learning tasks such as classification, regression, and density estimation. Exploratory data analysis (EDA) is initial and very important part of data analysis. In this thesis the concepts of exploratory spatial data analysis (ESDA) is considered using both traditional geostatistical approach such as_experimental variography and machine learning. Experimental variography is a basic tool for geostatistical analysis of anisotropic spatial correlations which helps to understand the presence of spatial patterns, at least described by two-point statistics. A machine learning approach for ESDA is presented by applying the k-nearest neighbors (k-NN) method which is simple and has very good interpretation and visualization properties. Important part of the thesis deals with a hot topic of nowadays, namely, an automatic mapping of geospatial data. General regression neural networks (GRNN) is proposed as efficient model to solve this task. Performance of the GRNN model is demonstrated on Spatial Interpolation Comparison (SIC) 2004 data where GRNN model significantly outperformed all other approaches, especially in case of emergency conditions. The thesis consists of four chapters and has the following structure: theory, applications, software tools, and how-to-do-it examples. An important part of the work is a collection of software tools - Machine Learning Office. Machine Learning Office tools were developed during last 15 years and was used both for many teaching courses, including international workshops in China, France, Italy, Ireland, Switzerland and for realizing fundamental and applied research projects. Case studies considered cover wide spectrum of the real-life low and high-dimensional geo- and environmental problems, such as air, soil and water pollution by radionuclides and heavy metals, soil types and hydro-geological units classification, decision-oriented mapping with uncertainties, natural hazards (landslides, avalanches) assessments and susceptibility mapping. Complementary tools useful for the exploratory data analysis and visualisation were developed as well. The software is user friendly and easy to use.

Evaluation of Recycled Rubber in Asphalt Concrete, HR-330, Construction Report, 1991

Discarded tires present major disposal and environmental problems. The recycling of those tires in asphalt cement concrete is what this research deals with. The Iowa DOT and the University of Northern Iowa (UNI) are evaluating the use of discarded tires in asphalt rubber cement and rubber chip mixes. The project is located on US 61 between Blue Grass and Muscatine in Muscatine County. It contains four rubberized asphalt sections and control sections. One section consists of reacted rubber asphalt cement used in both the binder and surface courses, and one section, both lanes, contains a rubber chip mix. The reacted rubber asphalt and the rubber chip mixes were laid in July 1991. The project construction went well with a few problems of shoving and cracking of the mat. This report contains information about procedures and tests that were run and those that will be run. It also has a cost comparison since this is a major concern with the use of asphalt rubber. Evaluation of this project will continue for five years. Three more research projects containing rubberized asphalt were constructed in 1991 and another is to be constructed in 1992.

Venäjälle suuntautuva tavaraliikenne ja sen ympäristöhaittojen minimointi

Tavaranvaihto Suomen itärajalla on aina ollut hyvin vilkasta. Neuvostoliiton romahtamisen jälkeen kauppaan tuli hetkellisesti erittäin syvä notkahdus, joka kääntyi voimakkaaksi nousuksi lähestyttäessä 1990-luvun puoliväliä. Pelkän vientikaupan oheen tuli välityskauppaa, sekä transitoliikennettä, jolla on ollut huomattavaa paikallista vaikutusta Kaakkois-Suomen työllisyyteen, sekä kuljetusalalle maanlaajuisestikin. Venäjän devalvaatio elokuussa 1998 romahdutti, sekä kaupan, että transitoliikenteen, mutta on sittemmin kääntynyt uuteen nousuun. Koko Venäjän tulevaisuus ja sitä kautta maamme itärajan liikennemäärät ovat varsin vaikeasti ennustettavissa, mutta todennäköisintä on Venäjän talouskasvun jatkuminen, jonka hyödyntämisessä ja tukemisessa myös Suomen tulisi olla. Liikennemäärien kasvu on aiheuttanut paikallisia ympäristöongelmia myös Suomen puolella rajaa. Ongelmat ovat kasaantuneet rajanylityspaikoille Nuijamaalle ja Vaalimaalle valtavien rekkajonojen myötä. Paikallisten asukkaiden elämän helpottamiseksi olisi valtiovallan pyrittävä kehittämään rajanylityspaikkoja, joista erityisesti Nuijamaa on käynyt jo kauan sitten liian pieneksi. Tekninen kehitys pienentää yksittäisen auton aiheuttamaa kuormitusta luonnolle, mutta liikennemäärien kasvu aiheuttaa kasaantuvia paikallisia ongelmia. Olemme toistaiseksi Suomessa EU:n itärajalla. Viron ja muiden Baltian maiden liittymiseen saakka, ja maantieteellisessä erityisasemassa koko unionin alueella. Samalla Suomen olisi muistettava, että meidän itärajalla on toistaiseksi maailman suurin elintasokuilu ja eurooppalainen vastakkain asettelu: EU vastaan Venäjä, länsi vastaan itä.

Recursos litosféricos y medio ambiente

This paper focuses that geological resources is an essential need in the development of the society and specially of the developing countries. Taking into account the processes and environmental problems related to mining exploitation, these activities should be performed in a environment concordance. For these reason al1 the available environmental techniques and tools for a responsible exploitation of resources should be used.

Assessment of Coastal Bird Populations and Habitats on the Finnish Coast of the Baltic Sea: Implications for Monitoring and Management

Coastal birds are an integral part of coastal ecosystems, which nowadays are subject to severe environmental pressures. Effective measures for the management and conservation of seabirds and their habitats call for insight into their population processes and the factors affecting their distribution and abundance. Central to national and international management and conservation measures is the availability of accurate data and information on bird populations, as well as on environmental trends and on measures taken to solve environmental problems. In this thesis I address different aspects of the occurrence, abundance, population trends and breeding success of waterbirds breeding on the Finnish coast of the Baltic Sea, and discuss the implications of the results for seabird monitoring, management and conservation. In addition, I assess the position and prospects of coastal bird monitoring data, in the processing and dissemination of biodiversity data and information in accordance with the Convention on Biological Diversity (CBD) and other national and international commitments. I show that important factors for seabird habitat selection are island area and elevation, water depth, shore openness, and the composition of island cover habitats. Habitat preferences are species-specific, with certain similarities within species groups. The occurrence of the colonial Arctic Tern (Sterna paradisaea) is partly affected by different habitat characteristics than its abundance. Using long-term bird monitoring data, I show that eutrophication and winter severity have reduced the populations of several Finnish seabird species. A major demographic factor through which environmental changes influence bird populations is breeding success. Breeding success can function as a more rapid indicator of sublethal environmental impacts than population trends, particularly for long-lived and slowbreeding species, and should therefore be included in coastal bird monitoring schemes. Among my target species, local breeding success can be shown to affect the populations of the Mallard (Anas platyrhynchos), the Eider (Somateria mollissima) and the Goosander (Mergus merganser) after a time lag corresponding to their species-specific recruitment age. For some of the target species, the number of individuals in late summer can be used as an easier and more cost-effective indicator of breeding success than brood counts. My results highlight that the interpretation and application of habitat and population studies require solid background knowledge of the ecology of the target species. In addition, the special characteristics of coastal birds, their habitats, and coastal bird monitoring data have to be considered in the assessment of their distribution and population trends. According to the results, the relationships between the occurrence, abundance and population trends of coastal birds and environmental factors can be quantitatively assessed using multivariate modelling and model selection. Spatial data sets widely available in Finland can be utilised in the calculation of several variables that are relevant to the habitat selection of Finnish coastal species. Concerning some habitat characteristics field work is still required, due to a lack of remotely sensed data or the low resolution of readily available data in relation to the fine scale of the habitat patches in the archipelago. While long-term data sets exist for water quality and weather, the lack of data concerning for instance the food resources of birds hampers more detailed studies of environmental effects on bird populations. Intensive studies of coastal bird species in different archipelago areas should be encouraged. The provision and free delivery of high-quality coastal data concerning bird populations and their habitats would greatly increase the capability of ecological modelling, as well as the management and conservation of coastal environments and communities. International initiatives that promote open spatial data infrastructures and sharing are therefore highly regarded. To function effectively, international information networks, such as the biodiversity Clearing House Mechanism (CHM) under the CBD, need to be rooted at regional and local levels. Attention should also be paid to the processing of data for higher levels of the information hierarchy, so that data are synthesized and developed into high-quality knowledge applicable to management and conservation.

Contribuição ao estudo de uma metodologia alternativa para obtenção de dioxissulfeto de terras raras

In the last decade, many method has been developed to obtain oxysufides. However, theses materials were obtained by reaction involved gaseous toxics, CO, CS2, H2S and S. In the present work, the synthesis of lanthanum oxysufides actived by europium (III) through an alternative method has been made. This method involve the rare earth sulfate reduction under an atmosphere of argon contained 10% hydrogen using the thermogravimetric technique. The results showed the formation of the phase TR2O2S (TR = La and Eu) at temperatures which depend upon the heating rate, respectively 650 - 830ºC at 5ºC min-1 and 680 - 800ºC at 10ºC min-1. The oxysufides obtained are characterized by infrared spectroscopy. The method developed is more economic than the usual industrial methods and the environmental problems during the synthesis are also better controled.

Electrochemistry and green chemical processes: electrochemical ozone production

After an introductory discussion emphasising the importance of electrochemistry for the so-called Green Chemical Processes, the article presents a short discussion of the classical ozone generation technologies. Next a revision of the electrochemical ozone production technology focusing on such aspects as: fundamentals, latest advances, advantages and limitations of this technology is presented. Recent results about fundamentals of electrochemical ozone production obtained in our laboratory, using different electrode materials (e.g. boron doped diamond electrodes, lead dioxide and DSAÒ-based electrodes) also are presented. Different chemical processes of interest to the solution of environmental problems involving ozone are discussed.

Marcos da história da radioatividade e tendências atuais

The first days of radioactivity, the discoveries of X-rays, radioactivity, of alpha- and beta- particles and gamma- radiation, of new radioactive elements, of artificial radioactivity, the neutron and positron and nuclear fission are reviewed as well as several adverse historical marks, such as the Manhattan project and some nuclear and radiological accidents. Nuclear energy generation in Brazil and the world, as an alternative to minimize environmental problems, is discussed, as are the medicinal, industrial and food applications of ionizing radiation. The text leads the reader to reflect on the subject and to consider its various aspects with scientific and technological maturity.

Bioaccumulation of metals in aquatic insects of streams located in areas with sugar cane cultivation

Streams located in areas of sugar cane cultivation receive elevated concentrations of metal ions from soils of adjacent areas. The accumulation of metals in the sediments results in environmental problems and leads to bioaccumulation of metal ions by the aquatic organisms. In the present study, bioaccumulation of the metals ions Al, Cd, Cr, Cu, Fe, Mg, Mn and Zn in aquatic insects in streams impacted by the sugar cane was evaluated. The results pointed out that the insects were contaminated by the sediment and that the collector organisms as Chironomus species accumulated higher concentration of metals than the predator organisms.

Químico-Biologia Quantitativa: um novo paradigma?

Disconcerting environmental problems, for which no solutions exist yet, appear daily. Despite this, many believe countries such as Brazil, biologically rich and not yet belonging to the First World, should be restricted to collecting information. Counteracting this opinion, that precludes rationally influencing the environment, we have sought to better understand the language of nature based on Quantitative Chemo-Biology. This multidisciplinary endeavor tackles a range of issues from basic questions such as the origin of life, to more urgent problems such as mapping the chemical and biological diversity of specific regions. We believe this is the right way to prepare younger generations to deal with the unpredictable future.

Química Sem Fronteiras: o desafio da energia

Coal, natural gas and petroleum-based liquid fuels are still the most widely used energy sources in modern society. The current scenario contrasts with the foreseen shortage of petroleum that was spread out in the beginning of the XXI century, when the concept of "energy security" emerged as an urgent agenda to ensure a good balance between energy supply and demand. Much beyond protecting refineries and oil ducts from terrorist attacks, these issues soon developed to a portfolio of measures related to process sustainability, involving at least three fundamental dimensions: (a) the need for technological breakthroughs to improve energy production worldwide; (b) the improvement of energy efficiency in all sectors of modern society; and (c) the increase of the social perception that education is a key-word towards a better use of our energy resources. Together with these technological, economic or social issues, "energy security" is also strongly influenced by environmental issues involving greenhouse gas emissions, loss of biodiversity in environmentally sensitive areas, pollution and poor solid waste management. For these and other reasons, the implementation of more sustainable practices in our currently available industrial facilities and the search for alternative energy sources that could partly replace the fossil fuels became a major priority throughout the world. Regarding fossil fuels, the main technological bottlenecks are related to the exploitation of less accessible petroleum resources such as those in the pre-salt layer, ranging from the proper characterization of these deep-water oil reservoirs, the development of lighter and more efficient equipment for both exploration and exploitation, the optimization of the drilling techniques, the achievement of further improvements in production yields and the establishment of specialized training programs for the technical staff. The production of natural gas from shale is also emerging in several countries but its production in large scale has several problems ranging from the unavoidable environmental impact of shale mining as well as to the bad consequences of its large scale exploitation in the past. The large scale use of coal has similar environmental problems, which are aggravated by difficulties in its proper characterization. Also, the mitigation of harmful gases and particulate matter that are released as a result of combustion is still depending on the development of new gas cleaning technologies including more efficient catalysts to improve its emission profile. On the other hand, biofuels are still struggling to fulfill their role in reducing our high dependence on fossil fuels. Fatty acid alkyl esters (biodiesel) from vegetable oils and ethanol from cane sucrose and corn starch are mature technologies whose market share is partially limited by the availability of their raw materials. For this reason, there has been a great effort to develop "second-generation" technologies to produce methanol, ethanol, butanol, biodiesel, biogas (methane), bio-oils, syngas and synthetic fuels from lower grade renewable feedstocks such as lignocellulosic materials whose consumption would not interfere with the rather sensitive issues of food security. Advanced fermentation processes are envisaged as "third generation" technologies and these are primarily linked to the use of algae feedstocks as well as other organisms that could produce biofuels or simply provide microbial biomass for the processes listed above. Due to the complexity and cost of their production chain, "third generation" technologies usually aim at high value added biofuels such as biojet fuel, biohydrogen and hydrocarbons with a fuel performance similar to diesel or gasoline, situations in which the use of genetically modified organisms is usually required. In general, the main challenges in this field could be summarized as follows: (a) the need for prospecting alternative sources of biomass that are not linked to the food chain; (b) the intensive use of green chemistry principles in our current industrial activities; (c) the development of mature technologies for the production of second and third generation biofuels; (d) the development of safe bioprocesses that are based on environmentally benign microorganisms; (e) the scale-up of potential technologies to a suitable demonstration scale; and (f) the full understanding of the technological and environmental implications of the food vs. fuel debate. On the basis of these, the main objective of this article is to stimulate the discussion and help the decision making regarding "energy security" issues and their challenges for modern society, in such a way to encourage the participation of the Brazilian Chemistry community in the design of a road map for a safer, sustainable and prosper future for our nation.

Estudo da liberação controlada do herbicida ametrina em compósitos à base de PVA: carvão ativado

Herbicides have great importance in agricultural productivity for weed control, given their competition with crops. However, inadequate application of herbicides may lead to environmental problems, which can be minimized through controlled release of the active compounds. This may be achieved by protecting the herbicide in a structure with adequate porosity, where the diffusional behavior can determine release. Thus, in this study we evaluated a novel structure, a composite based on activated carbon bonded by polyvinyl alcohol (PVA) as pellets, to deliver a triazine herbicide. The product obtained was shown to be adequate for its purpose, since it was possible to process regular pellets, where the PVA percentage determined the properties.

Fosforin kierron sulkeminen systeemi-innovaationa, case: Biomeri Oy

Phosphorus is a vital raw material but there is a threat that world's phosphorus reserves will diminish. It is essential to utilize phosphorus in order to feed world's population. Nevertheless phosphorus consumption causes some severe environmental problems. To solve these problems a large-scale change such as system innovation is required. System innovation is structural transition which influence on many interest groups and their interactions. One of the most potential solutions lie on phosphorus recovery. Unfortunately recovery faces many social barriers. This study examines case -company Biomeri Oy, because this company has developed an environmental innovation which meets the same problems as phosphorus recovery.

Integrating eco-innovation principles into regional strategy and policy: case of Päijät-Häme region, Finland

This study focuses on the integration of eco-innovation principles into strategy and policy at the regional level. The importance of regions as a level for integrating eco-innovative programs and activities served as the point of interest for this study. Eco-innovative activities and technologies are seen as means to meet sustainable development objective of improving regions’ quality of life. This study is conducted to get an in-depth understanding and learning about eco-innovation at regional level, and to know the basic concepts that are important in integrating eco-innovation principles into regional policy. Other specific objectives of this study are to know how eco-innovation are developed and practiced in the regions of the EU, and to analyze the main characteristic features of an eco-innovation model that is specifically developed at Päijät-Häme Region in Finland. Paijät-Häme Region is noted for its successful eco-innovation strategies and programs, hence, taken as casework in this study. Both primary (interviews) and secondary data (publicly available documents) are utilized in this study. The study shows that eco-innovation plays an important role in regional strategy as reviewed based on the experience of other regions in the EU. This is because of its localized nature which makes it easier to facilitate in a regional setting. Since regional authorities and policy-makers are normally focused on solving its localized environmental problems, eco-innovation principles can easily be integrated into regional strategy. The case study highlights Päijät-Häme Region’s eco-innovation strategies and projects which are characterized by strong connection of knowledge-producing institutions. Policy instruments supporting eco-innovation (e.g. environmental technologies) are very much focused on clean technologies, hence, justifying the formation of cleantech clusters and business parks in Päijät-Häme Region. A newly conceptualized SAMPO model of eco-innovation has been developed in Päijät-Häme Region to better capture the region’s characteristics and to eventually replace the current model employed by the Päijät-Häme Regional Authority. The SAMPO model is still under construction, however, review of its principles points to some of its three important spearheads – practice-based innovation, design (eco-design) and clean technology or environmental technology (environment).