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.

Modeling the Emergence of Social Structure from a Phylogenetic Point of View

Based on provious (Hemelrijk 1998; Puga-González, Hildenbrant & Hemelrijk 2009), we have developed an agent-based model and software, called A-KinGDom, which allows us to simulate the emergence of the social structure in a group of non-human primates. The model includes dominance and affiliative interactions and incorporate s two main innovations (preliminary dominance interactions and a kinship factor), which allow us to define four different attack and affiliative strategies. In accordance with these strategies, we compared the data obtained under four simulation conditions with the results obtained in a provious study (Dolado & Beltran 2012) involving empirical observations of a captive group of mangabeys (Cercocebus torquatus)

Modeling carbon sequestration and timber production in a regional case study

Abstract

Toxicokinetic modeling of folpet fungicide and its ring-biomarkers of exposure in humans.

A human in vivo toxicokinetic model was built to allow a better understanding of the toxicokinetics of folpet fungicide and its key ring biomarkers of exposure: phthalimide (PI), phthalamic acid (PAA) and phthalic acid (PA). Both PI and the sum of ring metabolites, expressed as PA equivalents (PAeq), may be used as biomarkers of exposure. The conceptual representation of the model was based on the analysis of the time course of these biomarkers in volunteers orally and dermally exposed to folpet. In the model, compartments were also used to represent the body burden of folpet and experimentally relevant PI, PAA and PA ring metabolites in blood and in key tissues as well as in excreta, hence urinary and feces. The time evolution of these biomarkers in each compartment of the model was then mathematically described by a system of coupled differential equations. The mathematical parameters of the model were then determined from best fits to the time courses of PI and PAeq in blood and urine of five volunteers administered orally 1 mg kg(-1) and dermally 10 mg kg(-1) of folpet. In the case of oral administration, the mean elimination half-life of PI from blood (through feces, urine or metabolism) was found to be 39.9 h as compared with 28.0 h for PAeq. In the case of a dermal application, mean elimination half-life of PI and PAeq was estimated to be 34.3 and 29.3 h, respectively. The average final fractions of administered dose recovered in urine as PI over the 0-96 h period were 0.030 and 0.002%, for oral and dermal exposure, respectively. Corresponding values for PAeq were 24.5 and 1.83%, respectively. Finally, the average clearance rate of PI from blood calculated from the oral and dermal data was 0.09 ± 0.03 and 0.13 ± 0.05 ml h(-1) while the volume of distribution was 4.30 ± 1.12 and 6.05 ± 2.22 l, respectively. It was not possible to obtain the corresponding values from PAeq data owing to the lack of blood time course data.

Neural networks complemented with genetic algorithms and fuzzy systems for predicting nitrogenous effluent variables in wastewater treatment plants

This work focuses on the prediction of the two main nitrogenous variables that describe the water quality at the effluent of a Wastewater Treatment Plant. We have developed two kind of Neural Networks architectures based on considering only one output or, in the other hand, the usual five effluent variables that define the water quality: suspended solids, biochemical organic matter, chemical organic matter, total nitrogen and total Kjedhal nitrogen. Two learning techniques based on a classical adaptative gradient and a Kalman filter have been implemented. In order to try to improve generalization and performance we have selected variables by means genetic algorithms and fuzzy systems. The training, testing and validation sets show that the final networks are able to learn enough well the simulated available data specially for the total nitrogen

Robust Nonlinear Mapping of Soil Contamination Using Support Regression

Spatial data analysis mapping and visualization is of great importance in various fields: environment, pollution, natural hazards and risks, epidemiology, spatial econometrics, etc. A basic task of spatial mapping is to make predictions based on some empirical data (measurements). A number of state-of-the-art methods can be used for the task: deterministic interpolations, methods of geostatistics: the family of kriging estimators (Deutsch and Journel, 1997), machine learning algorithms such as artificial neural networks (ANN) of different architectures, hybrid ANN-geostatistics models (Kanevski and Maignan, 2004; Kanevski et al., 1996), etc. All the methods mentioned above can be used for solving the problem of spatial data mapping. Environmental empirical data are always contaminated/corrupted by noise, and often with noise of unknown nature. That's one of the reasons why deterministic models can be inconsistent, since they treat the measurements as values of some unknown function that should be interpolated. Kriging estimators treat the measurements as the realization of some spatial randomn process. To obtain the estimation with kriging one has to model the spatial structure of the data: spatial correlation function or (semi-)variogram. This task can be complicated if there is not sufficient number of measurements and variogram is sensitive to outliers and extremes. ANN is a powerful tool, but it also suffers from the number of reasons. of a special type ? multiplayer perceptrons ? are often used as a detrending tool in hybrid (ANN+geostatistics) models (Kanevski and Maignank, 2004). Therefore, development and adaptation of the method that would be nonlinear and robust to noise in measurements, would deal with the small empirical datasets and which has solid mathematical background is of great importance. The present paper deals with such model, based on Statistical Learning Theory (SLT) - Support Vector Regression. SLT is a general mathematical framework devoted to the problem of estimation of the dependencies from empirical data (Hastie et al, 2004; Vapnik, 1998). SLT models for classification - Support Vector Machines - have shown good results on different machine learning tasks. The results of SVM classification of spatial data are also promising (Kanevski et al, 2002). The properties of SVM for regression - Support Vector Regression (SVR) are less studied. First results of the application of SVR for spatial mapping of physical quantities were obtained by the authorsin for mapping of medium porosity (Kanevski et al, 1999), and for mapping of radioactively contaminated territories (Kanevski and Canu, 2000). The present paper is devoted to further understanding of the properties of SVR model for spatial data analysis and mapping. Detailed description of the SVR theory can be found in (Cristianini and Shawe-Taylor, 2000; Smola, 1996) and basic equations for the nonlinear modeling are given in section 2. Section 3 discusses the application of SVR for spatial data mapping on the real case study - soil pollution by Cs137 radionuclide. Section 4 discusses the properties of the modelapplied to noised data or data with outliers.

Survey of prenatal screening policies in Europe for structural malformations and chromosome anomalies, and their impact on detection and termination rates for neural tube defects and Down's syndrome.

OBJECTIVE: To 'map' the current (2004) state of prenatal screening in Europe. DESIGN: (i) Survey of country policies and (ii) analysis of data from EUROCAT (European Surveillance of Congenital Anomalies) population-based congenital anomaly registers. SETTING: Europe. POPULATION: Survey of prenatal screening policies in 18 countries and 1.13 million births in 12 countries in 2002-04. METHODS: (i) Questionnaire on national screening policies and termination of pregnancy for fetal anomaly (TOPFA) laws in 2004. (ii) Analysis of data on prenatal detection and termination for Down's syndrome and neural tube defects (NTDs) using the EUROCAT database. MAIN OUTCOME MEASURES: Existence of national prenatal screening policies, legal gestation limit for TOPFA, prenatal detection and termination rates for Down's syndrome and NTD. RESULTS: Ten of the 18 countries had a national country-wide policy for Down's syndrome screening and 14/18 for structural anomaly scanning. Sixty-eight percent of Down's syndrome cases (range 0-95%) were detected prenatally, of which 88% resulted in termination of pregnancy. Eighty-eight percent (range 25-94%) of cases of NTD were prenatally detected, of which 88% resulted in termination. Countries with a first-trimester screening policy had the highest proportion of prenatally diagnosed Down's syndrome cases. Countries with no official national Down's syndrome screening or structural anomaly scan policy had the lowest proportion of prenatally diagnosed Down's syndrome and NTD cases. Six of the 18 countries had a legal gestational age limit for TOPFA, and in two countries, termination of pregnancy was illegal at any gestation. CONCLUSIONS: There are large differences in screening policies between countries in Europe. These, as well as organisational and cultural factors, are associated with wide country variation in prenatal detection rates for Down's syndrome and NTD.

Forecasting the Earth"s radiation belts and modeling solar energetic particle events: Recent results from SPACECAST

High-energy charged particles in the van Allen radiation belts and in solar energetic particle events can damage satellites on orbit leading to malfunctions and loss of satellite service. Here we describe some recent results from the SPACECAST project on modelling and forecasting the radiation belts, and modelling solar energetic particle events. We describe the SPACECAST forecasting system that uses physical models that include wave-particle interactions to forecast the electron radiation belts up to 3 h ahead. We show that the forecasts were able to reproduce the >2 MeV electron flux at GOES 13 during the moderate storm of 7-8 October 2012, and the period following a fast solar wind stream on 25-26 October 2012 to within a factor of 5 or so. At lower energies of 10- a few 100 keV we show that the electron flux at geostationary orbit depends sensitively on the high-energy tail of the source distribution near 10 RE on the nightside of the Earth, and that the source is best represented by a kappa distribution. We present a new model of whistler mode chorus determined from multiple satellite measurements which shows that the effects of wave-particle interactions beyond geostationary orbit are likely to be very significant. We also present radial diffusion coefficients calculated from satellite data at geostationary orbit which vary with Kp by over four orders of magnitude. We describe a new automated method to determine the position at the shock that is magnetically connected to the Earth for modelling solar energetic particle events and which takes into account entropy, and predict the form of the mean free path in the foreshock, and particle injection efficiency at the shock from analytical theory which can be tested in simulations.

Combining digital elevation model analysis and run-out modeling to characterize hazard posed by a potentially unstable rock slope at Turtle Mountain, Alberta, Canada

Turtle Mountain in Alberta, Canada has become an important field laboratory for testing different techniques related to the characterization and monitoring of large slope mass movements as the stability of large portions of the eastern face of the mountain is still questionable. In order to better quantify the volumes potentially unstable and the most probable failure mechanisms and potential consequences, structural analysis and runout modeling were preformed. The structural features of the eastern face were investigated using a high resolution digital elevation model (HRDEM). According to displacement datasets and structural observations, potential failure mechanisms affecting different portions of the mountain have been assessed. The volumes of the different potentially unstable blocks have been calculated using the Sloping Local Base Level (SLBL) method. Based on the volume estimation, two and three dimensional dynamic runout analyses have been performed. Calibration of this analysis is based on the experience from the adjacent Frank Slide and other similar rock avalanches. The results will be used to improve the contingency plans within the hazard area.

Neural substrates of social emotion regulation: a FMRI study on imitation and expressive suppression to dynamic facial signals.

Emotion regulation is crucial for successfully engaging in social interactions. Yet, little is known about the neural mechanisms controlling behavioral responses to emotional expressions perceived in the face of other people, which constitute a key element of interpersonal communication. Here, we investigated brain systems involved in social emotion perception and regulation, using functional magnetic resonance imaging (fMRI) in 20 healthy participants. The latter saw dynamic facial expressions of either happiness or sadness, and were asked to either imitate the expression or to suppress any expression on their own face (in addition to a gender judgment control task). fMRI results revealed higher activity in regions associated with emotion (e.g., the insula), motor function (e.g., motor cortex), and theory of mind (e.g., [pre]cuneus) during imitation. Activity in dorsal cingulate cortex was also increased during imitation, possibly reflecting greater action monitoring or conflict with own feeling states. In addition, premotor regions were more strongly activated during both imitation and suppression, suggesting a recruitment of motor control for both the production and inhibition of emotion expressions. Expressive suppression (eSUP) produced increases in dorsolateral and lateral prefrontal cortex typically related to cognitive control. These results suggest that voluntary imitation and eSUP modulate brain responses to emotional signals perceived from faces, by up- and down-regulating activity in distributed subcortical and cortical networks that are particularly involved in emotion, action monitoring, and cognitive control.

Modeling morphogen gradient formation from arbitrary realistically shaped sources.

Much of the analytical modeling of morphogen profiles is based on simplistic scenarios, where the source is abstracted to be point-like and fixed in time, and where only the steady state solution of the morphogen gradient in one dimension is considered. Here we develop a general formalism allowing to model diffusive gradient formation from an arbitrary source. This mathematical framework, based on the Green's function method, applies to various diffusion problems. In this paper, we illustrate our theory with the explicit example of the Bicoid gradient establishment in Drosophila embryos. The gradient formation arises by protein translation from a mRNA distribution followed by morphogen diffusion with linear degradation. We investigate quantitatively the influence of spatial extension and time evolution of the source on the morphogen profile. For different biologically meaningful cases, we obtain explicit analytical expressions for both the steady state and time-dependent 1D problems. We show that extended sources, whether of finite size or normally distributed, give rise to more realistic gradients compared to a single point-source at the origin. Furthermore, the steady state solutions are fully compatible with a decreasing exponential behavior of the profile. We also consider the case of a dynamic source (e.g. bicoid mRNA diffusion) for which a protein profile similar to the ones obtained from static sources can be achieved.

Public health impact of statin prescribing strategies based on JUPITER Modeling study from a population-based study.

OBJECTIVE: To evaluate the public health impact of statin prescribing strategies based on the Justification for the Use of Statins in Primary Prevention: An Intervention Trial Evaluating Rosuvastatin Study (JUPITER). METHODS: We studied 2268 adults aged 35-75 without cardiovascular disease in a population-based study in Switzerland in 2003-2006. We assessed the eligibility for statins according to the Adult Treatment Panel III (ATPIII) guidelines, and by adding "strict" (hs-CRP≥2.0mg/L and LDL-cholesterol <3.4mmol/L), and "extended" (hs-CRP≥2.0mg/L alone) JUPITER-like criteria. We estimated the proportion of CHD deaths potentially prevented over 10years in the Swiss population. RESULTS: Fifteen % were already taking statins, 42% were eligible by ATPIII guidelines, 53% by adding "strict", and 62% by adding "extended" criteria, with a total of 19% newly eligible. The number needed to treat with statins to avoid one CHD death over 10years was 38 for ATPIII, 84 for "strict" and 92 for "extended" JUPITER-like criteria. ATPIII would prevent 17% of CHD deaths, compared with 20% for ATPIII+"strict" and 23% for ATPIII + "extended" criteria (+6%). CONCLUSION: Implementing JUPITER-like strategies would make statin prescribing for primary prevention more common and less efficient than it is with current guidelines.