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.

Quand la nourriture se fait parole: Scènes de communication alimentaire dans les récits médiévaux

Depuis les travaux d'Anita Guerreau-Jalabert sur la symbolique des triangles alimentaires dans le roman arthurien, personne ne saurait douter qu'au Moyen Âge la nourriture obéit à des codes. Une scène de table ne se réduit pas à une notation à valeur référentielle, à un éclat de vie aristocratique : intégrée au récit, la notation alimentaire est un élément constitutif du sens de l'oeuvre. Plus particulièrement, un plat peut servir de message adressé par un personnage à un autre. On s'est peu intéressé, si ce n'est pour la légende du coeur mangé, à ces passages où la nourriture vient compléter, voire se substituer à la parole. Des nouvelles de Boccace (traduites par Laurent de Premierfait) aux Cent Nouvelles nouvelles et au Pogge (traduit par Guillaume Tardif), mais aussi dans les romans (Ysaÿe le Triste, Le Cuer d'amours espris, Jehan de Saintré), les exemples ne manquent pas qui, à la fin du Moyen Âge, illustrent la variété des messages alimentaires. Si le plat qu'on sert peut être l'instrument d'une vengeance (le repas cannibale !), il est aussi et surtout utilisé comme moyen de séduction. Parfois, il s'agit d'un avertissement qui, par la transgression des codes, donne voix à la morale ; ailleurs, l'ironie s'en mêle, quand la nourriture traduit une attitude de dérision face au convive. Ce dernier procédé, plus ludique, ne se rencontre pas seulement - comme on pourrait s'y attendre - dans l'univers du fabliau ou de la nouvelle. Il traverse le Moyen Âge et, du XIIe au XVe siècle, prépare l'émergence du cuisinier dont l'art et les « joyeux dits » font un double du poète.

Speaking from the Inside: Challenges Faced by Communication Researchers Investigating Disease-Related Issues in a Hospital Setting.

This commentary came from within the framework of integrating the humanities in medicine and from accompanying research on disease-related issues by teams involving clinicians and researchers in medical humanities. The purpose is to reflect on the challenges faced by researchers when conducting emotionally laden research and on how they impact observations and subsequent research findings. This commentary is furthermore a call to action since it promotes the institutionalization of a supportive context for medical humanities researchers who have not been trained to cope with sensitive medical topics in research. To that end, concrete recommendations regarding training and supervision were formulated.

Communication with terminal cancer patients in palliative care: are there differences between nurses and physicians?

The aim of this study was to find whether there were interprofessional differences in specific elements of communication with terminal cancer patients and decision-making processes that concern such patients. Given that interdisciplinary team work is one of the basic values in palliative care, if there are conflicting views between professions on such important issues it is most important to know about these and to understand them. A questionnaire utilized in an earlier survey of palliative care physicians and addressing their attitudes to and beliefs about specific elements of communication and decision making was sent to a sample of palliative care nurses working in the same regions, i.e. the French-speaking parts of Switzerland, Belgium and France. After a second mailing (reminder), 135 of the 163 questionnaires (83%) were returned. There was general agreement between nurses and physicians on questions dealing with perceptions of patients' knowledge of their diagnosis and stage of disease, patients' need for information, "do not resuscitate" orders and ethical principles in decision-making processes. Statistically significant, but small, differences between professional groups were only observed for a minority of the questions. Interprofessional differences in specific elements of communication with terminal cancer patients and decision-making processes affecting these patients were not so marked that they could be called "conflicting interprofessional views."

Communication skills training in oncology: it works!

While the previous chapter by L. Fallowfield and V. Jenkins focuses on different communication skills training (CST) concepts currently being utilized, this chapter reviews and comments the scientific evidence of the impact of CST on improving communication skills. The aim of this chapter is not to provide a complete review of the evidence-this has already been done in systematic reviews-but to discuss the scientific evidence and reflect on the available results and relevant topics for further investigations.

Texte et contexte dans la communication

DES FRONTIERES ENTRE TEXTE ET CONTEXTE : POINTS DE VUE THEORIQUES - Sur la métacommunication / C. Sluzki - De l'amour du texte à l'amour du contexte / J. Cosnier - Le dialogue entre l'intra-psychique et l'interpersonnel : une perspective développmentale / D. Stern - Texte et contexte. La perspective thermodynamique / R. Fivaz - Une position constructiviste pour la thérapie familiale / L. Hoffman MICROPROCESSUS DANS LES CONVERSATIONS : POINTS DE VUE EMPIRIQUES ET DEVELOPPEMENTAUX - Le contrat comme relation. Une étude des cadres sociaux du consentement / M. Modak - Recherche sur les axiomes de "Une logique de la communication" / J. Beavin-Bavelas - Distance physique ou distance psychique ? Les formations corporelles parents-bébé comme contextes de l'autonomisation dans la famille / C. Gertsch-Bettens - L'encadrement parental dans le jeu à trois. Une recherche exploratoire d'inspiration systémique / A. Corbosz-Warnery - L'évolution des formations corporelles lors de thérapies familiales en fonction de l'alliance thérapeutique / S. Serpa-Rusconi, P.-A. Doudin - Genèse de la négociation interpersonnelle des conflits : point de vue pragmatique / H. Jisa LES RECONTEXTUALISATIONS EN THERAPIE FAMILIALE - De l'ajustement du cadre en thérapie familiale / F. Seywert, E. Fivaz Depeursinge - Les questions réflexives, source d'autoguérison / K. Tomm...[et al.] - Langage et changement. L'usage de paroles-clés en thérapie / J. Pereira - Texte et contexte en psychosomatique : des modèles réductionnistes à une épistémologie de la complexité / L. Onnis

How siblings adjust sib-sib communication and begging signals to each other

Parents allocate food resources to their offspring in proportion to the intensity of begging behaviour. Begging encompasses several activities including vocalizations that should honestly signal need and jostling for the position in the nest where parents predictably deliver food items. Although siblings are known to adjust begging level to each other, the underlying mechanism remains unknown. We examined this issue in experimental two-chick broods of the barn owl, Tyto alba, a species in which siblings communicate vocally with each other in the prolonged absence of parents. The function of sib-sib vocal communication, so-called sibling negotiation, is to resolve conflicts over which individual will have priority of access to the next delivered indivisible food item. We found that when a nestling produced longer negotiation calls and stood closer to the nestbox entrance in the absence of parents, its sibling vocally negotiated at a lower rate. Additionally, when an individual produced more negotiation calls in the absence of parents, its sibling begged less intensely at the parent's return, with begging being the key factor that determined which nestling obtained a food item. We conclude that position in the nest and the duration of negotiation calls produced in the absence of parents influence the rate of producing negotiation calls, which in turn influences the rate at which siblings beg for food from their parents. Adjusting begging behaviour could therefore depend on complex sib-sib interactions taking place in the prolonged absence of parents.

The establishment of communication systems depends on the scale of competition

How communication systems emerge and remain stable is an important question in both cognitive science and evolutionary biology. For communication to arise, not only must individuals cooperate by signaling reliable information, but they must also coordinate and perpetuate signals. Most studies on the emergence of communication in humans typically consider scenarios where individuals implicitly share the same interests. Likewise, most studies on human cooperation consider scenarios where shared conventions of signals and meanings cannot be developed de novo. Here, we combined both approaches with an economic experiment where participants could develop a common language, but under different conditions fostering or hindering cooperation. Participants endeavored to acquire a resource through a learning task in a computer-based environment. After this task, participants had the option to transmit a signal (a color) to a fellow group member, who would subsequently play the same learning task. We varied the way participants competed with each other (either global scale or local scale) and the cost of transmitting a signal (either costly or noncostly) and tracked the way in which signals were used as communication among players. Under global competition, players signaled more often and more consistently, scored higher individual payoffs, and established shared associations of signals and meanings. In addition, costly signals were also more likely to be used under global competition; whereas under local competition, fewer signals were sent and no effective communication system was developed. Our results demonstrate that communication involves both a coordination and a cooperative dilemma and show the importance of studying language evolution under different conditions influencing human cooperation.

Towards Machine Consciousness: Grounding Abstract Models as pi-Processes

We present a two-level model of concurrent communicating systems (CCS) to serve as a basis formachine consciousness. A language implementing threads within logic programming is ¯rstintroduced. This high-level framework allows for the de¯nition of abstract processes that can beexecuted on a virtual machine. We then look for a possible grounding of these processes into thebrain. Towards this end, we map abstract de¯nitions (including logical expressions representingcompiled knowledge) into a variant of the pi-calculus. We illustrate this approach through aseries of examples extending from a purely reactive behavior to patterns of consciousness.

Attitudes and beliefs of palliative care physicians regarding communication with terminally ill cancer patients.

The subject of communication between palliative care physicians and their patients regarding their diagnosis and prognosis has not been extensively researched. The purpose of this survey was to compare the attitudes and beliefs of palliative care specialists regarding communication with the terminally ill in Europe, South America, and Canada. A sample of palliative care physicians from South America (Argentina and Brazil), French-speaking Europe, and Canada were identified, and posted a questionnaire. Physicians who stated that they practised palliative care at least 30% of their time were considered evaluable as palliative care specialists. Of a total of 272 questionnaires, 228 were returned (84%); and 182/228 (81%) respondents were considered to be palliative care specialists. Palliative care physicians in all three regions believed that cancer patients should be informed of their diagnosis and the terminal nature of their illness. Physicians reported that at least 60% of their patients knew their diagnosis and the terminal stage of their illness in 52% and 24% of cases in South America, and 69% and 38% of cases in Europe, respectively. All physicians agreed that 'do not resuscitate' orders should be present, and should be discussed with the patient in all cases. While 93% of Canadian physicians stated that at least 60% of their patients wanted to know about the terminal stage of their illness, only 18% of South American, and 26% of European physicians said this (P < 0.001). Similar results were found when the physicians were asked the percentage of families who want patients to know the terminal stage of their illness. However, almost all of the physicians agreed that if they had terminal cancer they would like to know. There was a significant association between patient based decision-making and female sex (P = 0.007), older age (P = 0.04), and physicians from Canada and South America (P < 0.001). Finally, in their daily decision making, South American physicians were significantly more likely to support beneficence and justice as compared with autonomy. Canadian physicians were more likely to support autonomy as compared with beneficence. In summary, our findings suggest that there are major regional differences in the attitudes and beliefs of physicians regarding communication at the end of life. More research is badly needed on the attitudes and beliefs of patients, families, and health care professionals in different regions of the world.

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.

Infant's triangular communication in "two for one" versus "two against one" family triangles: Case illustrations

Infants use their social competence very early to communicate not only in dyads but also in triads, in particular in the triangle they form with their mother and father. The development of this triangular communication is largely shaped by the ways the parents support or undermine each other in relation to their child. Whereas triangular communication is facilitated in "two for one" alliances, it is recruited in the service of regulating the parents' conflicts in "two against one" coalitions. These processes are manifest in toddlerhood and may be traced back to the coparenting alliance in formation during pregnancy.