Statistical learning theory for geospatial data. Case study: Aral sea

In recent years there has been an explosive growth in the development of adaptive and data driven methods. One of the efficient and data-driven approaches is based on statistical learning theory (Vapnik 1998). The theory is based on Structural Risk Minimisation (SRM) principle and has a solid statistical background. When applying SRM we are trying not only to reduce training error ? to fit the available data with a model, but also to reduce the complexity of the model and to reduce generalisation error. Many nonlinear learning procedures recently developed in neural networks and statistics can be understood and interpreted in terms of the structural risk minimisation inductive principle. A recent methodology based on SRM is called Support Vector Machines (SVM). At present SLT is still under intensive development and SVM find new areas of application (www.kernel-machines.org). SVM develop robust and non linear data models with excellent generalisation abilities that is very important both for monitoring and forecasting. SVM are extremely good when input space is high dimensional and training data set i not big enough to develop corresponding nonlinear model. Moreover, SVM use only support vectors to derive decision boundaries. It opens a way to sampling optimization, estimation of noise in data, quantification of data redundancy etc. Presentation of SVM for spatially distributed data is given in (Kanevski and Maignan 2004).

Active learning methods for remote sensing image classification

In this paper, we propose two active learning algorithms for semiautomatic definition of training samples in remote sensing image classification. Based on predefined heuristics, the classifier ranks the unlabeled pixels and automatically chooses those that are considered the most valuable for its improvement. Once the pixels have been selected, the analyst labels them manually and the process is iterated. Starting with a small and nonoptimal training set, the model itself builds the optimal set of samples which minimizes the classification error. We have applied the proposed algorithms to a variety of remote sensing data, including very high resolution and hyperspectral images, using support vector machines. Experimental results confirm the consistency of the methods. The required number of training samples can be reduced to 10% using the methods proposed, reaching the same level of accuracy as larger data sets. A comparison with a state-of-the-art active learning method, margin sampling, is provided, highlighting advantages of the methods proposed. The effect of spatial resolution and separability of the classes on the quality of the selection of pixels is also discussed.

Uncertainty Quantification with Support Vector Regression Prediction Models

Uncertainty quantification of petroleum reservoir models is one of the present challenges, which is usually approached with a wide range of geostatistical tools linked with statistical optimisation or/and inference algorithms. The paper considers a data driven approach in modelling uncertainty in spatial predictions. Proposed semi-supervised Support Vector Regression (SVR) model has demonstrated its capability to represent realistic features and describe stochastic variability and non-uniqueness of spatial properties. It is able to capture and preserve key spatial dependencies such as connectivity, which is often difficult to achieve with two-point geostatistical models. Semi-supervised SVR is designed to integrate various kinds of conditioning data and learn dependences from them. A stochastic semi-supervised SVR model is integrated into a Bayesian framework to quantify uncertainty with multiple models fitted to dynamic observations. The developed approach is illustrated with a reservoir case study. The resulting probabilistic production forecasts are described by uncertainty envelopes.

Analysis, modelling and classification of geospatial data using machine learning

The research considers the problem of spatial data classification using machine learning algorithms: probabilistic neural networks (PNN) and support vector machines (SVM). As a benchmark model simple k-nearest neighbor algorithm is considered. PNN is a neural network reformulation of well known nonparametric principles of probability density modeling using kernel density estimator and Bayesian optimal or maximum a posteriori decision rules. PNN is well suited to problems where not only predictions but also quantification of accuracy and integration of prior information are necessary. An important property of PNN is that they can be easily used in decision support systems dealing with problems of automatic classification. Support vector machine is an implementation of the principles of statistical learning theory for the classification tasks. Recently they were successfully applied for different environmental topics: classification of soil types and hydro-geological units, optimization of monitoring networks, susceptibility mapping of natural hazards. In the present paper both simulated and real data case studies (low and high dimensional) are considered. The main attention is paid to the detection and learning of spatial patterns by the algorithms applied.

Geomodelling of a fluvial system with semi-supervised support vector regression

Fluvial deposits are a challenge for modelling flow in sub-surface reservoirs. Connectivity and continuity of permeable bodies have a major impact on fluid flow in porous media. Contemporary object-based and multipoint statistics methods face a problem of robust representation of connected structures. An alternative approach to model petrophysical properties is based on machine learning algorithm ? Support Vector Regression (SVR). Semi-supervised SVR is able to establish spatial connectivity taking into account the prior knowledge on natural similarities. SVR as a learning algorithm is robust to noise and captures dependencies from all available data. Semi-supervised SVR applied to a synthetic fluvial reservoir demonstrated robust results, which are well matched to the flow performance

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.

Learning wind fields with multiple kernels

This paper presents multiple kernel learning (MKL) regression as an exploratory spatial data analysis and modelling tool. The MKL approach is introduced as an extension of support vector regression, where MKL uses dedicated kernels to divide a given task into sub-problems and to treat them separately in an effective way. It provides better interpretability to non-linear robust kernel regression at the cost of a more complex numerical optimization. In particular, we investigate the use of MKL as a tool that allows us to avoid using ad-hoc topographic indices as covariables in statistical models in complex terrains. Instead, MKL learns these relationships from the data in a non-parametric fashion. A study on data simulated from real terrain features confirms the ability of MKL to enhance the interpretability of data-driven models and to aid feature selection without degrading predictive performances. Here we examine the stability of the MKL algorithm with respect to the number of training data samples and to the presence of noise. The results of a real case study are also presented, where MKL is able to exploit a large set of terrain features computed at multiple spatial scales, when predicting mean wind speed in an Alpine region.

Monitoring network optimisation for spatial data classification using support vector machines

The paper presents a novel method for monitoring network optimisation, based on a recent machine learning technique known as support vector machine. It is problem-oriented in the sense that it directly answers the question of whether the advised spatial location is important for the classification model. The method can be used to increase the accuracy of classification models by taking a small number of additional measurements. Traditionally, network optimisation is performed by means of the analysis of the kriging variances. The comparison of the method with the traditional approach is presented on a real case study with climate data.

Supporting interdisciplinary case studies: development and implementation of a joint learning environment for students in forensic science and criminal law

Scientific reporting and communication is a challenging topic for which traditional study programs do not offer structured learning activities on a regular basis. This paper reports on the development and implementation of a web application and associated learning activities that intend to raise the awareness of reporting and communication issues among students in forensic science and law. The project covers interdisciplinary case studies based on a library of written reports about forensic examinations. Special features of the web framework, in particular a report annotation tool, support the design of various individual and group learning activities that focus on the development of knowledge and competence in dealing with reporting and communication challenges in the students' future areas of professional activity.

Multiple Kernel Learning of Environmental Data. Case study: Analysis and Mapping of Wind Fields

The paper presents the Multiple Kernel Learning (MKL) approach as a modelling and data exploratory tool and applies it to the problem of wind speed mapping. Support Vector Regression (SVR) is used to predict spatial variations of the mean wind speed from terrain features (slopes, terrain curvature, directional derivatives) generated at different spatial scales. Multiple Kernel Learning is applied to learn kernels for individual features and thematic feature subsets, both in the context of feature selection and optimal parameters determination. An empirical study on real-life data confirms the usefulness of MKL as a tool that enhances the interpretability of data-driven models.

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.

Auditory cues support place navigation in rats when associated with a visual cue.

Rats, like other crepuscular animals, have excellent auditory capacities and they discriminate well between different sounds [Heffner HE, Heffner RS, Hearing in two cricetid rodents: wood rats (Neotoma floridana) and grasshopper mouse (Onychomys leucogaster). J Comp Psychol 1985;99(3):275-88]. However, most experimental literature concerning spatial orientation almost exclusively emphasizes the use of visual landmarks [Cressant A, Muller RU, Poucet B. Failure of centrally placed objects to control the firing fields of hippocampal place cells. J Neurosci 1997;17(7):2531-42; and Goodridge JP, Taube JS. Preferential use of the landmark navigational system by head direction cells in rats. Behav Neurosci 1995;109(1):49-61]. To address the important issue of whether rats are able to achieve a place navigation task relative to auditory beacons, we designed a place learning task in the water maze. We controlled cue availability by conducting the experiment in total darkness. Three auditory cues did not allow place navigation whereas three visual cues in the same positions did support place navigation. One auditory beacon directly associated with the goal location did not support taxon navigation (a beacon strategy allowing the animal to find the goal just by swimming toward the cue). Replacing the auditory beacons by one single visual beacon did support taxon navigation. A multimodal configuration of two auditory cues and one visual cue allowed correct place navigation. The deletion of the two auditory or of the one visual cue did disrupt the spatial performance. Thus rats can combine information from different sensory modalities to achieve a place navigation task. In particular, auditory cues support place navigation when associated with a visual one.

Ensemble methods for environmental data modelling with support vector regression

This paper investigates the use of ensemble of predictors in order to improve the performance of spatial prediction methods. Support vector regression (SVR), a popular method from the field of statistical machine learning, is used. Several instances of SVR are combined using different data sampling schemes (bagging and boosting). Bagging shows good performance, and proves to be more computationally efficient than training a single SVR model while reducing error. Boosting, however, does not improve results on this specific problem.

Basic life support teaching in the second year predraduate medical curriculum: quality of acquisition after 6 months

Purpose of the study: Basic life support (BLS) and automated externaldefibrillation (AED) represent important skills to be acquired duringpregraduate medical training. Since 3 years, our medical school hasintroduced a BLS-AED course (with certification) for all second yearmedical students. Few reports about quality and persistence over timeof BLS-AED learning are available to date in the medical literature.Comprehensive evaluation of students' acquired skills was performedat the end of the 2008 academic year, 6 month after certification.Materials and methods: The students (N = 142) were evaluated duringa 9 minutes «objective structured clinical examination» (OSCE) station.Out of a standardized scenario, they had to recognize a cardiac arrestsituation and start a resuscitation process. Their performance wererecorded on a PC using an Ambuman(TM) mannequin and the AmbuCPR software kit(TM) during a minimum of 8 cycles (30 compressions:2 ventilations each). BLS parameters were systematically checked. Nostudent-rater interactions were allowed during the whole evaluation.Results: Response of the victim was checked by 99% of the students(N = 140), 96% (N = 136) called for an ambulance and/or an AED. Openthe airway and check breathing were done by 96% (N = 137), 92% (N =132) gave 2 rescue breaths. Pulse was checked by 95% (N=135), 100%(N = 142) begun chest compression, 96% (N = 136) within 1 minute.Chest compression rate was 101 ± 18 per minute (mean ± SD), depthcompression 43 ± 8 mm, 97% (N = 138) respected a compressionventilationratio of 30:2.Conclusions: Quality of BLS skills acquisition is maintained during a6-month period after a BLS-AED certification. Main targets of 2005 AHAguidelines were well respected. This analysis represents one of thelargest evaluations of specific BLS teaching efficiency reported. Furtherfollow-up is needed to control the persistence of these skills during alonger time period and noteworthy at the end of the pregraduatemedical curriculum.

Data-driven topo-climatic mapping with machine learning methods

Automatic environmental monitoring networks enforced by wireless communication technologies provide large and ever increasing volumes of data nowadays. The use of this information in natural hazard research is an important issue. Particularly useful for risk assessment and decision making are the spatial maps of hazard-related parameters produced from point observations and available auxiliary information. The purpose of this article is to present and explore the appropriate tools to process large amounts of available data and produce predictions at fine spatial scales. These are the algorithms of machine learning, which are aimed at non-parametric robust modelling of non-linear dependencies from empirical data. The computational efficiency of the data-driven methods allows producing the prediction maps in real time which makes them superior to physical models for the operational use in risk assessment and mitigation. Particularly, this situation encounters in spatial prediction of climatic variables (topo-climatic mapping). In complex topographies of the mountainous regions, the meteorological processes are highly influenced by the relief. The article shows how these relations, possibly regionalized and non-linear, can be modelled from data using the information from digital elevation models. The particular illustration of the developed methodology concerns the mapping of temperatures (including the situations of Föhn and temperature inversion) given the measurements taken from the Swiss meteorological monitoring network. The range of the methods used in the study includes data-driven feature selection, support vector algorithms and artificial neural networks.