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.

EasyStrata: evaluation and visualization of stratified genome-wide association meta-analysis data.

The R package EasyStrata facilitates the evaluation and visualization of stratified genome-wide association meta-analyses (GWAMAs) results. It provides (i) statistical methods to test and account for between-strata difference as a means to tackle gene-strata interaction effects and (ii) extended graphical features tailored for stratified GWAMA results. The software provides further features also suitable for general GWAMAs including functions to annotate, exclude or highlight specific loci in plots or to extract independent subsets of loci from genome-wide datasets. It is freely available and includes a user-friendly scripting interface that simplifies data handling and allows for combining statistical and graphical functions in a flexible fashion. AVAILABILITY: EasyStrata is available for free (under the GNU General Public License v3) from our Web site www.genepi-regensburg.de/easystrata and from the CRAN R package repository cran.r-project.org/web/packages/EasyStrata/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

"Soap-Bubble" visualization and quantitative analysis of 3D coronary magnetic resonance angiograms.

In order to compare coronary magnetic resonance angiography (MRA) data obtained with different scanning methodologies, adequate visualization and presentation of the coronary MRA data need to be ensured. Furthermore, an objective quantitative comparison between images acquired with different scanning methods is desirable. To address this need, a software tool ("Soap-Bubble") that facilitates visualization and quantitative comparison of 3D volume targeted coronary MRA data was developed. In the present implementation, the user interactively specifies a curved subvolume (enclosed in the 3D coronary MRA data set) that closely encompasses the coronary arterial segments. With a 3D Delaunay triangulation and a parallel projection, this enables the simultaneous display of multiple coronary segments in one 2D representation. For objective quantitative analysis, frequently explored quantitative parameters such as signal-to-noise ratio (SNR); contrast-to-noise ratio (CNR); and vessel length, sharpness, and diameter can be assessed. The present tool supports visualization and objective, quantitative comparisons of coronary MRA data obtained with different scanning methods. The first results obtained in healthy adults and in patients with coronary artery disease are presented.

VariScan Software

VariScan is a software package for the analysis of DNA sequence polymorphisms at the whole genome scale. Among other features, the software:(1) can conduct many population genetic analyses; (2) incorporates a multiresolution wavelet transform-based method that allows capturing relevant information from DNA polymorphism data; and (3) it facilitates the visualization of the results in the most commonly used genome browsers.

Capaware: plataforma de desarrollo de software libre para aplicacines geográficas 3D multicapa

En este trabajo se presenta Capaware, una plataforma de software libre para el desarrollo de aplicaciones geográficas 3D multicapa, que surge a partir de la iniciativa del Instituto Tecnológico de Canarias en colaboración con la Universidad de Las Palmas de Gran Canaria. Este entorno simplifica la creación de aplicaciones 3D sobre territorios geográficos extensos, disponiendo de una herramienta muy visual que aporta un nuevo punto de vista muy importante para una toma de decisiones eficaz. Capaware proporciona una interfaz fácil de usar y muy flexible que simplifica el desarrollo de nuevas aplicaciones, permitiéndonos crear rápidamente entornos virtuales con múltiples capas de información sobre el terreno. Con las capacidades clásicas de un Sistema de Información Geográfica (SIG), Capaware permite actualmente la carga de capas WMS sobre entornos 3D, añadir objetos 3D sobre el terreno, y visualizar elementos dinámicos, ofreciendo una nueva perspectiva de la información analizada. Así mismo, podemos administrar las capas de recursos y elementos que se pueden representar sobre la zona geográfica en cuestión. (...)

GODIVA2: interactive visualization of environmental data on the Web

GODIVA2 is a dynamic website that provides visual access to several terabytes of physically distributed, four-dimensional environmental data. It allows users to explore large datasets interactively without the need to install new software or download and understand complex data. Through the use of open international standards, GODIVA2 maintains a high level of interoperability with third-party systems, allowing diverse datasets to be mutually compared. Scientists can use the system to search for features in large datasets and to diagnose the output from numerical simulations and data processing algorithms. Data providers around Europe have adopted GODIVA2 as an INSPIRE-compliant dynamic quick-view system for providing visual access to their data.

A Web Map Service implementation for the visualization of multidimensional gridded environmental data

We describe ncWMS, an implementation of the Open Geospatial Consortium’s Web Map Service (WMS) specification for multidimensional gridded environmental data. ncWMS can read data in a large number of common scientific data formats – notably the NetCDF format with the Climate and Forecast conventions – then efficiently generate map imagery in thousands of different coordinate reference systems. It is designed to require minimal configuration from the system administrator and, when used in conjunction with a suitable client tool, provides end users with an interactive means for visualizing data without the need to download large files or interpret complex metadata. It is also used as a “bridging” tool providing interoperability between the environmental science community and users of geographic information systems. ncWMS implements a number of extensions to the WMS standard in order to fulfil some common scientific requirements, including the ability to generate plots representing timeseries and vertical sections. We discuss these extensions and their impact upon present and future interoperability. We discuss the conceptual mapping between the WMS data model and the data models used by gridded data formats, highlighting areas in which the mapping is incomplete or ambiguous. We discuss the architecture of the system and particular technical innovations of note, including the algorithms used for fast data reading and image generation. ncWMS has been widely adopted within the environmental data community and we discuss some of the ways in which the software is integrated within data infrastructures and portals.

Developing a mobile visualization environment for construction applications

There is a renewed interest in immersive visualization to navigate digital data-sets associated with large building and infrastructure projects. Following work with a fully immersive visualization facility at the University, this paper details the development of a complementary mobile visualization environment. It articulates progress on the requirements for this facility; the overall design of hardware and software; and the laboratory testing and planning for user pilots in construction applications. Like our fixed facility, this new light-weight mobile solution enables a group of users to navigate a 3D model at a 1:1 scale and to work collaboratively with structured asset information. However it offers greater flexibility as two users can assemble and start using it at a new location within an hour. The solution has been developed and tested in a laboratory and will be piloted in engineering design review and stakeholder engagement applications on a major construction project.

PedVis: A Structured, Space-Efficient Technique for Pedigree Visualization

Public genealogical databases are becoming increasingly populated with historical data and records of the current population`s ancestors. As this increasing amount of available information is used to link individuals to their ancestors, the resulting trees become deeper and more dense, which justifies the need for using organized, space-efficient layouts to display the data. Existing layouts are often only able to show a small subset of the data at a time. As a result, it is easy to become lost when navigating through the data or to lose sight of the overall tree structure. On the contrary, leaving space for unknown ancestors allows one to better understand the tree`s structure, but leaving this space becomes expensive and allows fewer generations to be displayed at a time. In this work, we propose that the H-tree based layout be used in genealogical software to display ancestral trees. We will show that this layout presents an increase in the number of displayable generations, provides a nicely arranged, symmetrical, intuitive and organized fractal structure, increases the user`s ability to understand and navigate through the data, and accounts for the visualization requirements necessary for displaying such trees. Finally, user-study results indicate potential for user acceptance of the new layout.

Verifiable Visualization for Isosurface Extraction

Visual representations of isosurfaces are ubiquitous in the scientific and engineering literature. In this paper, we present techniques to assess the behavior of isosurface extraction codes. Where applicable, these techniques allow us to distinguish whether anomalies in isosurface features can be attributed to the underlying physical process or to artifacts from the extraction process. Such scientific scrutiny is at the heart of verifiable visualization - subjecting visualization algorithms to the same verification process that is used in other components of the scientific pipeline. More concretely, we derive formulas for the expected order of accuracy (or convergence rate) of several isosurface features, and compare them to experimentally observed results in the selected codes. This technique is practical: in two cases, it exposed actual problems in implementations. We provide the reader with the range of responses they can expect to encounter with isosurface techniques, both under ""normal operating conditions"" and also under adverse conditions. Armed with this information - the results of the verification process - practitioners can judiciously select the isosurface extraction technique appropriate for their problem of interest, and have confidence in its behavior.

Enhanced visualization of histological samples with an adjustable RGB contrast system with application for tissue used in photodynamic therapy

The analysis of histological sections has long been a valuable tool in the pathological studies. The interpretation of tissue conditions, however, relies directly on visual evaluation of tissue slides, which may be difficult to interpret because of poor contrast or poor color differentiation. The Chromatic Contrast Visualization System (CCV) combines an optical microscope with electronically controlled light-emitting diodes (LEDs) in order to generate adjustable intensities of RGB channels for sample illumination. While most image enhancement techniques rely on software post-processing of an image acquired under standard illumination conditions, CCV produces real-time variations in the color composition of the light source itself. The possibility of covering the entire RGB chromatic range, combined with the optical properties of the different tissues, allows for a substantial enhancement in image details. Traditional image acquisition methods do not exploit these visual enhancements which results in poorer visual distinction among tissue structures. Photodynamic therapy (PDT) procedures are of increasing interest in the treatment of several forms of cancer. This study uses histological slides of rat liver samples that were induced to necrosis after being exposed to PDT. Results show that visualization of tissue structures could be improved by changing colors and intensities of the microscope light source. PDT-necrosed tissue samples are better differentiated when illuminated with different color wavelengths, leading to an improved differentiation of cells in the necrosis area. Due to the potential benefits it can bring to interpretation and diagnosis, further research in this field could make CCV an attractive technique for medical applications.

Advanced Building Energy Data Visualization

Advanced Building Energy Data Visualization is a way to detect performance problems in commercialbuildings. By placing sensors in a building that collects data from example, air temperature and electricalpower, then makes it possible to calculate the data in Data Visualization software. This softwaregenerates visual diagrams so the building manager or building operator can see if for example thepower consumption is to high.A first step (before sensors are installed in a building) to see how the energy consumption is in abuilding can be to use a Benchmarking Tool. There is a number of Benchmarking Tools that is availablefor free on the Internet. Each tool have a bit different approach, but they all show how much energyconsumption there is in a building compared to other similar buildings.In this study a new web design for the benchmarking tool CalARCH has been developed. CalARCHis developed at the Berkeley Lab in Berkeley, California, USA. CalARCH uses data collected only frombuildings in California, and is only for comparing buildings in California with other similar buildingsin the state.Five different versions of the web site were made. Then a web survey was done to determine whichversion would be the best for CalARCH. The results showed that Version 5 and Version 3 was the best.Then a new version was made, based on these two versions. This study was made at the LawrenceBerkeley Laboratory.

Software Tools For Large Scale Interactive Hydrodynamic Modeling

Running hydrodynamic models interactively allows both visual exploration and change of model state during simulation. One of the main characteristics of an interactive model is that it should provide immediate feedback to the user, for example respond to changes in model state or view settings. For this reason, such features are usually only available for models with a relatively small number of computational cells, which are used mainly for demonstration and educational purposes. It would be useful if interactive modeling would also work for models typically used in consultancy projects involving large scale simulations. This results in a number of technical challenges related to the combination of the model itself and the visualisation tools (scalability, implementation of an appropriate API for control and access to the internal state). While model parallelisation is increasingly addressed by the environmental modeling community, little effort has been spent on developing a high-performance interactive environment. What can we learn from other high-end visualisation domains such as 3D animation, gaming, virtual globes (Autodesk 3ds Max, Second Life, Google Earth) that also focus on efficient interaction with 3D environments? In these domains high efficiency is usually achieved by the use of computer graphics algorithms such as surface simplification depending on current view, distance to objects, and efficient caching of the aggregated representation of object meshes. We investigate how these algorithms can be re-used in the context of interactive hydrodynamic modeling without significant changes to the model code and allowing model operation on both multi-core CPU personal computers and high-performance computer clusters.

Uma arquitetura de software baseada em componentes visualização de informações industriais

Due to the current need of the industry to integrate data of the beginning of production originating from of several sources and of transforming them in useful information for sockets of decisions, a search exists every time larger for systems of visualization of information that come to collaborate with that functionality. On the other hand, a common practice nowadays, due to the high competitiveness of the market, it is the development of industrial systems that possess characteristics of modularity, distribution, flexibility, scalability, adaptation, interoperability, reusability and access through web. Those characteristics provide an extra agility and a larger easiness in adapting to the frequent changes of demand of the market. Based on the arguments exposed above, this work consists of specifying a component-based architecture, with the respective development of a system based on that architecture, for the visualization of industrial data. The system was conceived to be capable to supply on-line information and, optionally, historical information of variables originating from of the beginning of production. In this work it is shown that the component-based architecture developed possesses the necessary requirements for the obtaining of a system robust, reliable and of easy maintenance, being, like this, in agreement with the industrial needs. The use of that architecture allows although components can be added, removed or updated in time of execution, through a manager of components through web, still activating more the adaptation process and updating of the system