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.

Mechanism of hcnA mRNA recognition in the Gac/Rsm signal transduction pathway of Pseudomonas fluorescens.

In the plant-beneficial bacterium Pseudomonas fluorescens CHA0, the expression of antifungal exoproducts is controlled by the GacS/GacA two-component system. Two RNA binding proteins (RsmA, RsmE) ensure effective translational repression of exoproduct mRNAs. At high cell population densities, GacA induces three small RNAs (RsmX, RsmY, RsmZ) which sequester both RsmA and RsmE, thereby relieving translational repression. Here we systematically analyse the features that allow the RNA binding proteins to interact strongly with the 5' untranslated leader mRNA of the P. fluorescens hcnA gene (encoding hydrogen cyanide synthase subunit A). We obtained evidence for three major RsmA/RsmE recognition elements in the hcnA leader, based on directed mutagenesis, RsmE footprints and toeprints, and in vivo expression data. Two recognition elements were found in two stem-loop structures whose existence in the 5' leader region was confirmed by lead(II) cleavage analysis. The third recognition element, which overlapped the hcnA Shine-Dalgarno sequence, was postulated to adopt either an open conformation, which would favour ribosome binding, or a stem-loop structure, which may form upon interaction with RsmA/RsmE and would inhibit access of ribosomes. Effective control of hcnA expression by the Gac/Rsm system appears to result from the combination of the three appropriately spaced recognition elements.

Effects of epitope modification on T cell receptor-ligand binding and antigen recognition by seven H-2Kd-restricted cytotoxic T lymphocyte clones specific for a photoreactive peptide derivative.

We tested for antigen recognition and T cell receptor (TCR)-ligand binding 12 peptide derivative variants on seven H-2Kd-restricted cytotoxic T lymphocytes (CTL) clones specific for a bifunctional photoreactive derivative of the Plasmodium berghei circumsporozoite peptide 252-260 (SYIPSAEKI). The derivative contained iodo-4-azidosalicylic acid in place of PbCS S-252 and 4-azidobenzoic acid on PbCS K-259. Selective photoactivation of the N-terminal photoreactive group allowed crosslinking to Kd molecules and photoactivation of the orthogonal group to TCR. TCR photoaffinity labeling with covalent Kd-peptide derivative complexes allowed direct assessment of TCR-ligand binding on living CTL. In most cases (over 80%) cytotoxicity (chromium release) and TCR-ligand binding differed by less than fivefold. The exceptions included (a) partial TCR agonists (8 cases), for which antigen recognition was five-tenfold less efficient than TCR-ligand binding, (b) TCR antagonists (2 cases), which were not recognized and capable of inhibiting recognition of the wild-type conjugate, (c) heteroclitic agonists (2 cases), for which antigen recognition was more efficient than TCR-ligand binding, and (d) one partial TCR agonist, which activated only Fas (C1)95), but not perforin/granzyme-mediated cytotoxicity. There was no correlation between these divergences and the avidity of TCR-ligand binding, indicating that other factors than binding avidity determine the nature of the CTL response. An unexpected and novel finding was that CD8-dependent clones clearly incline more to TCR antagonism than CD8-independent ones. As there was no correlation between CD8 dependence and the avidity of TCR-ligand binding, the possibility is suggested that CD8 plays a critical role in aberrant CTL function.

Etalonnage de trois épreuves de recognition continue : Effets de l'âge, du sexe et du niveau socio-professionnel sur les mesures de discrimination et de biais de réponse. [Standardization of three continuous recognition test forms - Effects of age, sex and socio-economic level on measurements of discrimination and response bias.]

Nous présontons l'étalonnage d'un test mnésique de recognition dans un échantillon de 180 adultes francophones de la Suisse Romande. Le test comprend trois formes utilisant un matériel verbal (mots) ou non verbal (visages ou paysages). Une attention particulière est accordée à l'âge dans la présentation des résultats. Celui-ci affecte plus précocement et plus intensément la performance aux formes non verbales qu'à la forme verbale du test. Il induit également une importante augmentation du nombre de fausses reconnaissances pour les formes non verbales.

Unicoloniality, recognition and genetic differentiation in a native Formica ant.

Some ants have an extraordinary form of social organization, called unicoloniality, whereby individuals mix freely among physically separated nests. This mode of social organization has been primarily studied in introduced and invasive ant species, so that the recognition ability and genetic structure of ants forming unicolonial populations in their native range remain poorly known. We investigated the pattern of aggression and the genetic structure of six unicolonial populations of the ant Formica paralugubris at four hierarchical levels: within nests, among nests within the same population, among nests of populations within the Alps or Jura Mountains and among nests of the two mountain ranges. Ants within populations showed no aggressive behaviour, but recognized nonnestmates as shown by longer antennation bouts. Overall, the level of aggression increased with geographic and genetic distance but was always considerably lower than between species. No distinct behavioural supercolony boundaries were found. Our study provides evidence that unicoloniality can be maintained in noninvasive ants despite significant genetic differentiation and the ability to discriminate between nestmates and nonnestmates.

On the evolution of harming and recognition in finite panmictic and infinite structured populations.

Natural selection may favor two very different types of social behaviors that have costs in vital rates (fecundity and/or survival) to the actor: helping behaviors, which increase the vital rates of recipients, and harming behaviors, which reduce the vital rates of recipients. Although social evolutionary theory has mainly dealt with helping behaviors, competition for limited resources creates ecological conditions in which an actor may benefit from expressing behaviors that reduce the vital rates of neighbors. This may occur if the reduction in vital rates decreases the intensity of competition experienced by the actor or that experienced by its offspring. Here, we explore the joint evolution of neutral recognition markers and marker-based costly conditional harming whereby actors express harming, conditional on actor and recipient bearing different conspicuous markers. We do so for two complementary demographic scenarios: finite panmictic and infinite structured populations. We find that marker-based conditional harming can evolve under a large range of recombination rates and group sizes under both finite panmictic and infinite structured populations. A direct comparison with results for the evolution of marker-based conditional helping reveals that, if everything else is equal, marker-based conditional harming is often more likely to evolve than marker-based conditional helping.

Nuclear translocation and DNA recognition signals colocalized within the bZIP domain of cyclic adenosine 3',5'-monophosphate response element-binding protein CREB.

CREB is a cAMP-responsive nuclear DNA-binding protein that binds to cAMP response elements and stimulates gene transcription upon activation of the cAMP signalling pathway. The protein consists of an amino-terminal transcriptional transactivation domain and a carboxyl-terminal DNA-binding domain (bZIP domain) comprised of a basic region and a leucine zipper involved in DNA recognition and dimerization, respectively. Recently, we discovered a testis-specific transcript of CREB that contains an alternatively spliced exon encoding multiple stop codons. CREB encoded by this transcript is a truncated protein lacking the bZIP domain. We postulated that the antigen detected by CREB antiserum in the cytoplasm of germinal cells is the truncated CREB that must also lack its nuclear translocation signal (NTS). To test this hypothesis we prepared multiple expression plasmids encoding carboxyl-terminal deletions of CREB and transiently expressed them in COS-1 cells. By Western immunoblot analysis as well as immunocytochemistry of transfected cells, we show that CREB proteins truncated to amino acid 286 or shorter are sequestered in the cytoplasm, whereas a CREB of 295 amino acids is translocated into the nucleus. Chimeric CREBs containing a heterologous NTS fused to the first 248 or 261 amino acids of CREB are able to drive the translocation of the protein into the nucleus. Thus, the nine amino acids in the basic region involved in DNA recognition between positions 287 and 295 (RRKKKEYVK) of CREB contain the NTS. Further, mutation of the lysine at position 290 in CREB to an asparagine diminishes nuclear translocation of the protein.(ABSTRACT TRUNCATED AT 250 WORDS)

Membrane insertion and antibody recognition of a glycosylphosphatidylinositol-anchored protein: an optical study.

The kinetics of binding of a glycolipid-anchored protein (the promastigote surface protease, PSP) to planar lecithin bilayers is studied by an integrated optics technique, in which the bilayer membrane is supported on an optical wave guide and the phase velocities of guided light modes in the wave guide are measured. From these velocities, the optical parameters of the membrane and PSP layers deposited on the waveguide are determined, yielding in particular the mass of PSP bound to the membrane, which is followed in real time. From a comparison of the binding rates of PSP and PSP from which the lipid moiety has been removed, it is shown that the lipid moiety plays a key role in anchoring the protein to the membrane. Specific and nonspecific binding of antibodies to membrane-anchored PSP is also investigated. As little as a fifth of a monolayer of PSP is sufficient to suppress the appreciable nonspecific binding of antibodies to the membrane.

Recognition of Gram-positive Intestinal Bacteria by Hybridoma- and Colostrum-derived Secretory Immunoglobulin A Is Mediated by Carbohydrates.

Humans live in symbiosis with 10(14) commensal bacteria among which >99% resides in their gastrointestinal tract. The molecular bases pertaining to the interaction between mucosal secretory IgA (SIgA) and bacteria residing in the intestine are not known. Previous studies have demonstrated that commensals are naturally coated by SIgA in the gut lumen. Thus, understanding how natural SIgA interacts with commensal bacteria can provide new clues on its multiple functions at mucosal surfaces. Using fluorescently labeled, nonspecific SIgA or secretory component (SC), we visualized by confocal microscopy the interaction with various commensal bacteria, including Lactobacillus, Bifidobacteria, Escherichia coli, and Bacteroides strains. These experiments revealed that the interaction between SIgA and commensal bacteria involves Fab- and Fc-independent structural motifs, featuring SC as a crucial partner. Removal of glycans present on free SC or bound in SIgA resulted in a drastic drop in the interaction with Gram-positive bacteria, indicating the essential role of carbohydrates in the process. In contrast, poor binding of Gram-positive bacteria by control IgG was observed. The interaction with Gram-negative bacteria was preserved whatever the molecular form of protein partner used, suggesting the involvement of different binding motifs. Purified SIgA and SC from either mouse hybridoma cells or human colostrum exhibited identical patterns of recognition for Gram-positive bacteria, emphasizing conserved plasticity between species. Thus, sugar-mediated binding of commensals by SIgA highlights the currently underappreciated role of glycans in mediating the interaction between a highly diverse microbiota and the mucosal immune system.

T cell recognition of hapten. Anatomy of T cell receptor binding of a H-2kd-associated photoreactive peptide derivative.

To elucidate the structural basis of T cell recognition of hapten-modified antigenic peptides, we studied the interaction of the T1 T cell antigen receptor (TCR) with its ligand, the H-2Kd-bound Plasmodium berghei circumsporozoite peptide 252-260 (SYIPSAEKI) containing photoreactive 4-azidobenzoic acid (ABA) on P. berghei circumsporozoite Lys259. The photoaffinity-labeled TCR residue(s) were mapped as Tyr48 and/or Tyr50 of complementary determining region 2beta (CDR2beta). Other TCR-ligand contacts were identified by mutational analysis. Molecular modeling, based on crystallographic coordinates of closely related TCR and major histocompatibility complex I molecules, indicated that ABA binds strongly and specifically in a cavity between CDR3alpha and CDR2beta. We conclude that TCR expressing selective Vbeta and CDR3alpha sequences form a binding domain between CDR3alpha and CDR2beta that can accommodate nonpeptidic moieties conjugated at the C-terminal portion of peptides binding to major histocompatibility complex (MHC) encoded proteins.

Repeatability in automatic sorting of curved Norway spruce saw logs

Abstract

A survey on automatic recommenders in the context of institutional repositories

Peer-reviewed

Is It Possible to Predict the Manual Web Accessibility Result Using the Automatic Result?

The most adequate approach for benchmarking web accessibility is manual expert evaluation supplemented by automatic analysis tools. But manual evaluation has a high cost and is impractical to be applied on large websites. In reality, there is no choice but to rely on automated tools when reviewing large web sites for accessibility. The question is: to what extent the results from automatic evaluation of a web site and individual web pages can be used as an approximation for manual results? This paper presents the initial results of an investigation aimed at answering this question. He have performed both manual and automatic evaluations of the accessibility of web pages of two sites and we have compared the results. In our data set automatically retrieved results could most definitely be used as an approximation manual evaluation results.