Advanced geostatistical and machine-learning models for spatial data analysis of radioactively contaminated regions

Radioactive soil-contamination mapping and risk assessment is a vital issue for decision makers. Traditional approaches for mapping the spatial concentration of radionuclides employ various regression-based models, which usually provide a single-value prediction realization accompanied (in some cases) by estimation error. Such approaches do not provide the capability for rigorous uncertainty quantification or probabilistic mapping. Machine learning is a recent and fast-developing approach based on learning patterns and information from data. Artificial neural networks for prediction mapping have been especially powerful in combination with spatial statistics. A data-driven approach provides the opportunity to integrate additional relevant information about spatial phenomena into a prediction model for more accurate spatial estimates and associated uncertainty. Machine-learning algorithms can also be used for a wider spectrum of problems than before: classification, probability density estimation, and so forth. Stochastic simulations are used to model spatial variability and uncertainty. Unlike regression models, they provide multiple realizations of a particular spatial pattern that allow uncertainty and risk quantification. This paper reviews the most recent methods of spatial data analysis, prediction, and risk mapping, based on machine learning and stochastic simulations in comparison with more traditional regression models. The radioactive fallout from the Chernobyl Nuclear Power Plant accident is used to illustrate the application of the models for prediction and classification problems. This fallout is a unique case study that provides the challenging task of analyzing huge amounts of data ('hard' direct measurements, as well as supplementary information and expert estimates) and solving particular decision-oriented problems.

Applying machine learning methods to avalanche forecasting

Avalanche forecasting is a complex process involving the assimilation of multiple data sources to make predictions over varying spatial and temporal resolutions. Numerically assisted forecasting often uses nearest neighbour methods (NN), which are known to have limitations when dealing with high dimensional data. We apply Support Vector Machines to a dataset from Lochaber, Scotland to assess their applicability in avalanche forecasting. Support Vector Machines (SVMs) belong to a family of theoretically based techniques from machine learning and are designed to deal with high dimensional data. Initial experiments showed that SVMs gave results which were comparable with NN for categorical and probabilistic forecasts. Experiments utilising the ability of SVMs to deal with high dimensionality in producing a spatial forecast show promise, but require further work.

Machine learning for spatial environmental data. Theory, applications and software

The book presents the state of the art in machine learning algorithms (artificial neural networks of different architectures, support vector machines, etc.) as applied to the classification and mapping of spatially distributed environmental data. Basic geostatistical algorithms are presented as well. New trends in machine learning and their application to spatial data are given, and real case studies based on environmental and pollution data are carried out. The book provides a CD-ROM with the Machine Learning Office software, including sample sets of data, that will allow both students and researchers to put the concepts rapidly to practice.

Could machine learning improve the prediction of pelvic nodal status of prostate cancer patients? Preliminary results of a pilot study.

We tested and compared performances of Roach formula, Partin tables and of three Machine Learning (ML) based algorithms based on decision trees in identifying N+ prostate cancer (PC). 1,555 cN0 and 50 cN+ PC were analyzed. Results were also verified on an independent population of 204 operated cN0 patients, with a known pN status (187 pN0, 17 pN1 patients). ML performed better, also when tested on the surgical population, with accuracy, specificity, and sensitivity ranging between 48-86%, 35-91%, and 17-79%, respectively. ML potentially allows better prediction of the nodal status of PC, potentially allowing a better tailoring of pelvic irradiation.

Personalized modeling for drug concentration prediction using Support Vector Machine

Building a personalized model to describe the drug concentration inside the human body for each patient is highly important to the clinical practice and demanding to the modeling tools. Instead of using traditional explicit methods, in this paper we propose a machine learning approach to describe the relation between the drug concentration and patients' features. Machine learning has been largely applied to analyze data in various domains, but it is still new to personalized medicine, especially dose individualization. We focus mainly on the prediction of the drug concentrations as well as the analysis of different features' influence. Models are built based on Support Vector Machine and the prediction results are compared with the traditional analytical models.

Time Series Input Selection using Multiple Kernel Learning

In this paper we study the relevance of multiple kernel learning (MKL) for the automatic selection of time series inputs. Recently, MKL has gained great attention in the machine learning community due to its flexibility in modelling complex patterns and performing feature selection. In general, MKL constructs the kernel as a weighted linear combination of basis kernels, exploiting different sources of information. An efficient algorithm wrapping a Support Vector Regression model for optimizing the MKL weights, named SimpleMKL, is used for the analysis. In this sense, MKL performs feature selection by discarding inputs/kernels with low or null weights. The approach proposed is tested with simulated linear and nonlinear time series (AutoRegressive, Henon and Lorenz series).

GeoKernels: Modeling of Spatial Data on GeoManifolds

This paper presents a review of methodology for semi-supervised modeling with kernel methods, when the manifold assumption is guaranteed to be satisfied. It concerns environmental data modeling on natural manifolds, such as complex topographies of the mountainous regions, where environmental processes are highly influenced by the relief. These relations, possibly regionalized and nonlinear, can be modeled from data with machine learning using the digital elevation models in semi-supervised kernel methods. The range of the tools and methodological issues discussed in the study includes feature selection and semisupervised Support Vector algorithms. The real case study devoted to data-driven modeling of meteorological fields illustrates the discussed approach.

Strategy selection: An introduction to the modeling challenge

Modeling the mechanisms that determine how humans and other agents choose among different behavioral and cognitive processes-be they strategies, routines, actions, or operators-represents a paramount theoretical stumbling block across disciplines, ranging from the cognitive and decision sciences to economics, biology, and machine learning. By using the cognitive and decision sciences as a case study, we provide an introduction to what is also known as the strategy selection problem. First, we explain why many researchers assume humans and other animals to come equipped with a repertoire of behavioral and cognitive processes. Second, we expose three descriptive, predictive, and prescriptive challenges that are common to all disciplines which aim to model the choice among these processes. Third, we give an overview of different approaches to strategy selection. These include cost‐benefit, ecological, learning, memory, unified, connectionist, sequential sampling, and maximization approaches. We conclude by pointing to opportunities for future research and by stressing that the selection problem is far from being resolved.

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.

Multi-scale systems analysis of plant development : beyond cellular signaling and tissue morphodynamics

Les plantes sont essentielles pour les sociétés humaines. Notre alimentation quotidienne, les matériaux de constructions et les sources énergétiques dérivent de la biomasse végétale. En revanche, la compréhension des multiples aspects développementaux des plantes est encore peu exploitée et représente un sujet de recherche majeur pour la science. L'émergence des technologies à haut débit pour le séquençage de génome à grande échelle ou l'imagerie de haute résolution permet à présent de produire des quantités énormes d'information. L'analyse informatique est une façon d'intégrer ces données et de réduire la complexité apparente vers une échelle d'abstraction appropriée, dont la finalité est de fournir des perspectives de recherches ciblées. Ceci représente la raison première de cette thèse. En d'autres termes, nous appliquons des méthodes descriptives et prédictives combinées à des simulations numériques afin d'apporter des solutions originales à des problèmes relatifs à la morphogénèse à l'échelle de la cellule et de l'organe. Nous nous sommes fixés parmi les objectifs principaux de cette thèse d'élucider de quelle manière l'interaction croisée des phytohormones auxine et brassinosteroïdes (BRs) détermine la croissance de la cellule dans la racine du méristème apical d'Arabidopsis thaliana, l'organisme modèle de référence pour les études moléculaires en plantes. Pour reconstruire le réseau de signalement cellulaire, nous avons extrait de la littérature les informations pertinentes concernant les relations entre les protéines impliquées dans la transduction des signaux hormonaux. Le réseau a ensuite été modélisé en utilisant un formalisme logique et qualitatif pour pallier l'absence de données quantitatives. Tout d'abord, Les résultats ont permis de confirmer que l'auxine et les BRs agissent en synergie pour contrôler la croissance de la cellule, puis, d'expliquer des observations phénotypiques paradoxales et au final, de mettre à jour une interaction clef entre deux protéines dans la maintenance du méristème de la racine. Une étude ultérieure chez la plante modèle Brachypodium dystachion (Brachypo- dium) a révélé l'ajustement du réseau d'interaction croisée entre auxine et éthylène par rapport à Arabidopsis. Chez ce dernier, interférer avec la biosynthèse de l'auxine mène à la formation d'une racine courte. Néanmoins, nous avons isolé chez Brachypodium un mutant hypomorphique dans la biosynthèse de l'auxine qui affiche une racine plus longue. Nous avons alors conduit une analyse morphométrique qui a confirmé que des cellules plus anisotropique (plus fines et longues) sont à l'origine de ce phénotype racinaire. Des analyses plus approfondies ont démontré que la différence phénotypique entre Brachypodium et Arabidopsis s'explique par une inversion de la fonction régulatrice dans la relation entre le réseau de signalisation par l'éthylène et la biosynthèse de l'auxine. L'analyse morphométrique utilisée dans l'étude précédente exploite le pipeline de traitement d'image de notre méthode d'histologie quantitative. Pendant la croissance secondaire, la symétrie bilatérale de l'hypocotyle est remplacée par une symétrie radiale et une organisation concentrique des tissus constitutifs. Ces tissus sont initialement composés d'une douzaine de cellules mais peuvent aisément atteindre des dizaines de milliers dans les derniers stades du développement. Cette échelle dépasse largement le seuil d'investigation par les moyens dits 'traditionnels' comme l'imagerie directe de tissus en profondeur. L'étude de ce système pendant cette phase de développement ne peut se faire qu'en réalisant des coupes fines de l'organe, ce qui empêche une compréhension des phénomènes cellulaires dynamiques sous-jacents. Nous y avons remédié en proposant une stratégie originale nommée, histologie quantitative. De fait, nous avons extrait l'information contenue dans des images de très haute résolution de sections transverses d'hypocotyles en utilisant un pipeline d'analyse et de segmentation d'image à grande échelle. Nous l'avons ensuite combiné avec un algorithme de reconnaissance automatique des cellules. Cet outil nous a permis de réaliser une description quantitative de la progression de la croissance secondaire révélant des schémas développementales non-apparents avec une inspection visuelle classique. La formation de pôle de phloèmes en structure répétée et espacée entre eux d'une longueur constante illustre les bénéfices de notre approche. Par ailleurs, l'exploitation approfondie de ces résultats a montré un changement de croissance anisotropique des cellules du cambium et du phloème qui semble en phase avec l'expansion du xylème. Combinant des outils génétiques et de la modélisation biomécanique, nous avons démontré que seule la croissance plus rapide des tissus internes peut produire une réorientation de l'axe de croissance anisotropique des tissus périphériques. Cette prédiction a été confirmée par le calcul du ratio des taux de croissance du xylème et du phloème au cours de développement secondaire ; des ratios élevés sont effectivement observés et concomitant à l'établissement progressif et tangentiel du cambium. Ces résultats suggèrent un mécanisme d'auto-organisation établi par un gradient de division méristématique qui génèrent une distribution de contraintes mécaniques. Ceci réoriente la croissance anisotropique des tissus périphériques pour supporter la croissance secondaire. - Plants are essential for human society, because our daily food, construction materials and sustainable energy are derived from plant biomass. Yet, despite this importance, the multiple developmental aspects of plants are still poorly understood and represent a major challenge for science. With the emergence of high throughput devices for genome sequencing and high-resolution imaging, data has never been so easy to collect, generating huge amounts of information. Computational analysis is one way to integrate those data and to decrease the apparent complexity towards an appropriate scale of abstraction with the aim to eventually provide new answers and direct further research perspectives. This is the motivation behind this thesis work, i.e. the application of descriptive and predictive analytics combined with computational modeling to answer problems that revolve around morphogenesis at the subcellular and organ scale. One of the goals of this thesis is to elucidate how the auxin-brassinosteroid phytohormone interaction determines the cell growth in the root apical meristem of Arabidopsis thaliana (Arabidopsis), the plant model of reference for molecular studies. The pertinent information about signaling protein relationships was obtained through the literature to reconstruct the entire hormonal crosstalk. Due to a lack of quantitative information, we employed a qualitative modeling formalism. This work permitted to confirm the synergistic effect of the hormonal crosstalk on cell elongation, to explain some of our paradoxical mutant phenotypes and to predict a novel interaction between the BREVIS RADIX (BRX) protein and the transcription factor MONOPTEROS (MP),which turned out to be critical for the maintenance of the root meristem. On the same subcellular scale, another study in the monocot model Brachypodium dystachion (Brachypodium) revealed an alternative wiring of auxin-ethylene crosstalk as compared to Arabidopsis. In the latter, increasing interference with auxin biosynthesis results in progressively shorter roots. By contrast, a hypomorphic Brachypodium mutant isolated in this study in an enzyme of the auxin biosynthesis pathway displayed a dramatically longer seminal root. Our morphometric analysis confirmed that more anisotropic cells (thinner and longer) are principally responsible for the mutant root phenotype. Further characterization pointed towards an inverted regulatory logic in the relation between ethylene signaling and auxin biosynthesis in Brachypodium as compared to Arabidopsis, which explains the phenotypic discrepancy. Finally, the morphometric analysis of hypocotyl secondary growth that we applied in this study was performed with the image-processing pipeline of our quantitative histology method. During its secondary growth, the hypocotyl reorganizes its primary bilateral symmetry to a radial symmetry of highly specialized tissues comprising several thousand cells, starting with a few dozens. However, such a scale only permits observations in thin cross-sections, severely hampering a comprehensive analysis of the morphodynamics involved. Our quantitative histology strategy overcomes this limitation. We acquired hypocotyl cross-sections from tiled high-resolution images and extracted their information content using custom high-throughput image processing and segmentation. Coupled with an automated cell type recognition algorithm, it allows precise quantitative characterization of vascular development and reveals developmental patterns that were not evident from visual inspection, for example the steady interspace distance of the phloem poles. Further analyses indicated a change in growth anisotropy of cambial and phloem cells, which appeared in phase with the expansion of xylem. Combining genetic tools and computational modeling, we showed that the reorientation of growth anisotropy axis of peripheral tissue layers only occurs when the growth rate of central tissue is higher than the peripheral one. This was confirmed by the calculation of the ratio of the growth rate xylem to phloem throughout secondary growth. High ratios are indeed observed and concomitant with the homogenization of cambium anisotropy. These results suggest a self-organization mechanism, promoted by a gradient of division in the cambium that generates a pattern of mechanical constraints. This, in turn, reorients the growth anisotropy of peripheral tissues to sustain the secondary growth.

What do we gain from simplicity versus complexity in species distribution models?

Species distribution models (SDMs) are widely used to explain and predict species ranges and environmental niches. They are most commonly constructed by inferring species' occurrence-environment relationships using statistical and machine-learning methods. The variety of methods that can be used to construct SDMs (e.g. generalized linear/additive models, tree-based models, maximum entropy, etc.), and the variety of ways that such models can be implemented, permits substantial flexibility in SDM complexity. Building models with an appropriate amount of complexity for the study objectives is critical for robust inference. We characterize complexity as the shape of the inferred occurrence-environment relationships and the number of parameters used to describe them, and search for insights into whether additional complexity is informative or superfluous. By building 'under fit' models, having insufficient flexibility to describe observed occurrence-environment relationships, we risk misunderstanding the factors shaping species distributions. By building 'over fit' models, with excessive flexibility, we risk inadvertently ascribing pattern to noise or building opaque models. However, model selection can be challenging, especially when comparing models constructed under different modeling approaches. Here we argue for a more pragmatic approach: researchers should constrain the complexity of their models based on study objective, attributes of the data, and an understanding of how these interact with the underlying biological processes. We discuss guidelines for balancing under fitting with over fitting and consequently how complexity affects decisions made during model building. Although some generalities are possible, our discussion reflects differences in opinions that favor simpler versus more complex models. We conclude that combining insights from both simple and complex SDM building approaches best advances our knowledge of current and future species ranges.

Mapping of Environmental Data Using Kernel-Based Methods

Recently, kernel-based Machine Learning methods have gained great popularity in many data analysis and data mining fields: pattern recognition, biocomputing, speech and vision, engineering, remote sensing etc. The paper describes the use of kernel methods to approach the processing of large datasets from environmental monitoring networks. Several typical problems of the environmental sciences and their solutions provided by kernel-based methods are considered: classification of categorical data (soil type classification), mapping of environmental and pollution continuous information (pollution of soil by radionuclides), mapping with auxiliary information (climatic data from Aral Sea region). The promising developments, such as automatic emergency hot spot detection and monitoring network optimization are discussed as well.

Example-based support vector machine for drug concentration analysis

Machine learning has been largely applied to analyze data in various domains, but it is still new to personalized medicine, especially dose individualization. In this paper, we focus on the prediction of drug concentrations using Support Vector Machines (S VM) and the analysis of the influence of each feature to the prediction results. Our study shows that SVM-based approaches achieve similar prediction results compared with pharmacokinetic model. The two proposed example-based SVM methods demonstrate that the individual features help to increase the accuracy in the predictions of drug concentration with a reduced library of training data.

Community Policing in Switzerland's Major Urban Areas: An Observational Study of the Implementation and Impact Using Geospatial Data Mining

La présente étude est à la fois une évaluation du processus de la mise en oeuvre et des impacts de la police de proximité dans les cinq plus grandes zones urbaines de Suisse - Bâle, Berne, Genève, Lausanne et Zurich. La police de proximité (community policing) est à la fois une philosophie et une stratégie organisationnelle qui favorise un partenariat renouvelé entre la police et les communautés locales dans le but de résoudre les problèmes relatifs à la sécurité et à l'ordre public. L'évaluation de processus a analysé des données relatives aux réformes internes de la police qui ont été obtenues par l'intermédiaire d'entretiens semi-structurés avec des administrateurs clés des cinq départements de police, ainsi que dans des documents écrits de la police et d'autres sources publiques. L'évaluation des impacts, quant à elle, s'est basée sur des variables contextuelles telles que des statistiques policières et des données de recensement, ainsi que sur des indicateurs d'impacts construit à partir des données du Swiss Crime Survey (SCS) relatives au sentiment d'insécurité, à la perception du désordre public et à la satisfaction de la population à l'égard de la police. Le SCS est un sondage régulier qui a permis d'interroger des habitants des cinq grandes zones urbaines à plusieurs reprises depuis le milieu des années 1980. L'évaluation de processus a abouti à un « Calendrier des activités » visant à créer des données de panel permettant de mesurer les progrès réalisés dans la mise en oeuvre de la police de proximité à l'aide d'une grille d'évaluation à six dimensions à des intervalles de cinq ans entre 1990 et 2010. L'évaluation des impacts, effectuée ex post facto, a utilisé un concept de recherche non-expérimental (observational design) dans le but d'analyser les impacts de différents modèles de police de proximité dans des zones comparables à travers les cinq villes étudiées. Les quartiers urbains, délimités par zone de code postal, ont ainsi été regroupés par l'intermédiaire d'une typologie réalisée à l'aide d'algorithmes d'apprentissage automatique (machine learning). Des algorithmes supervisés et non supervisés ont été utilisés sur les données à haute dimensionnalité relatives à la criminalité, à la structure socio-économique et démographique et au cadre bâti dans le but de regrouper les quartiers urbains les plus similaires dans des clusters. D'abord, les cartes auto-organisatrices (self-organizing maps) ont été utilisées dans le but de réduire la variance intra-cluster des variables contextuelles et de maximiser simultanément la variance inter-cluster des réponses au sondage. Ensuite, l'algorithme des forêts d'arbres décisionnels (random forests) a permis à la fois d'évaluer la pertinence de la typologie de quartier élaborée et de sélectionner les variables contextuelles clés afin de construire un modèle parcimonieux faisant un minimum d'erreurs de classification. Enfin, pour l'analyse des impacts, la méthode des appariements des coefficients de propension (propensity score matching) a été utilisée pour équilibrer les échantillons prétest-posttest en termes d'âge, de sexe et de niveau d'éducation des répondants au sein de chaque type de quartier ainsi identifié dans chacune des villes, avant d'effectuer un test statistique de la différence observée dans les indicateurs d'impacts. De plus, tous les résultats statistiquement significatifs ont été soumis à une analyse de sensibilité (sensitivity analysis) afin d'évaluer leur robustesse face à un biais potentiel dû à des covariables non observées. L'étude relève qu'au cours des quinze dernières années, les cinq services de police ont entamé des réformes majeures de leur organisation ainsi que de leurs stratégies opérationnelles et qu'ils ont noué des partenariats stratégiques afin de mettre en oeuvre la police de proximité. La typologie de quartier développée a abouti à une réduction de la variance intra-cluster des variables contextuelles et permet d'expliquer une partie significative de la variance inter-cluster des indicateurs d'impacts avant la mise en oeuvre du traitement. Ceci semble suggérer que les méthodes de géocomputation aident à équilibrer les covariables observées et donc à réduire les menaces relatives à la validité interne d'un concept de recherche non-expérimental. Enfin, l'analyse des impacts a révélé que le sentiment d'insécurité a diminué de manière significative pendant la période 2000-2005 dans les quartiers se trouvant à l'intérieur et autour des centres-villes de Berne et de Zurich. Ces améliorations sont assez robustes face à des biais dus à des covariables inobservées et covarient dans le temps et l'espace avec la mise en oeuvre de la police de proximité. L'hypothèse alternative envisageant que les diminutions observées dans le sentiment d'insécurité soient, partiellement, un résultat des interventions policières de proximité semble donc être aussi plausible que l'hypothèse nulle considérant l'absence absolue d'effet. Ceci, même si le concept de recherche non-expérimental mis en oeuvre ne peut pas complètement exclure la sélection et la régression à la moyenne comme explications alternatives. The current research project is both a process and impact evaluation of community policing in Switzerland's five major urban areas - Basel, Bern, Geneva, Lausanne, and Zurich. Community policing is both a philosophy and an organizational strategy that promotes a renewed partnership between the police and the community to solve problems of crime and disorder. The process evaluation data on police internal reforms were obtained through semi-structured interviews with key administrators from the five police departments as well as from police internal documents and additional public sources. The impact evaluation uses official crime records and census statistics as contextual variables as well as Swiss Crime Survey (SCS) data on fear of crime, perceptions of disorder, and public attitudes towards the police as outcome measures. The SCS is a standing survey instrument that has polled residents of the five urban areas repeatedly since the mid-1980s. The process evaluation produced a "Calendar of Action" to create panel data to measure community policing implementation progress over six evaluative dimensions in intervals of five years between 1990 and 2010. The impact evaluation, carried out ex post facto, uses an observational design that analyzes the impact of the different community policing models between matched comparison areas across the five cities. Using ZIP code districts as proxies for urban neighborhoods, geospatial data mining algorithms serve to develop a neighborhood typology in order to match the comparison areas. To this end, both unsupervised and supervised algorithms are used to analyze high-dimensional data on crime, the socio-economic and demographic structure, and the built environment in order to classify urban neighborhoods into clusters of similar type. In a first step, self-organizing maps serve as tools to develop a clustering algorithm that reduces the within-cluster variance in the contextual variables and simultaneously maximizes the between-cluster variance in survey responses. The random forests algorithm then serves to assess the appropriateness of the resulting neighborhood typology and to select the key contextual variables in order to build a parsimonious model that makes a minimum of classification errors. Finally, for the impact analysis, propensity score matching methods are used to match the survey respondents of the pretest and posttest samples on age, gender, and their level of education for each neighborhood type identified within each city, before conducting a statistical test of the observed difference in the outcome measures. Moreover, all significant results were subjected to a sensitivity analysis to assess the robustness of these findings in the face of potential bias due to some unobserved covariates. The study finds that over the last fifteen years, all five police departments have undertaken major reforms of their internal organization and operating strategies and forged strategic partnerships in order to implement community policing. The resulting neighborhood typology reduced the within-cluster variance of the contextual variables and accounted for a significant share of the between-cluster variance in the outcome measures prior to treatment, suggesting that geocomputational methods help to balance the observed covariates and hence to reduce threats to the internal validity of an observational design. Finally, the impact analysis revealed that fear of crime dropped significantly over the 2000-2005 period in the neighborhoods in and around the urban centers of Bern and Zurich. These improvements are fairly robust in the face of bias due to some unobserved covariate and covary temporally and spatially with the implementation of community policing. The alternative hypothesis that the observed reductions in fear of crime were at least in part a result of community policing interventions thus appears at least as plausible as the null hypothesis of absolutely no effect, even if the observational design cannot completely rule out selection and regression to the mean as alternative explanations.