Machine learning algorithms for spatial data. Case studies: Environmental pollution, natural hazards, renewable resources

This paper presents general problems and approaches for the spatial data analysis using machine learning algorithms. Machine learning is a very powerful approach to adaptive data analysis, modelling and visualisation. The key feature of the machine learning algorithms is that they learn from empirical data and can be used in cases when the modelled environmental phenomena are hidden, nonlinear, noisy and highly variable in space and in time. Most of the machines learning algorithms are universal and adaptive modelling tools developed to solve basic problems of learning from data: classification/pattern recognition, regression/mapping and probability density modelling. In the present report some of the widely used machine learning algorithms, namely artificial neural networks (ANN) of different architectures and Support Vector Machines (SVM), are adapted to the problems of the analysis and modelling of geo-spatial data. Machine learning algorithms have an important advantage over traditional models of spatial statistics when problems are considered in a high dimensional geo-feature spaces, when the dimension of space exceeds 5. Such features are usually generated, for example, from digital elevation models, remote sensing images, etc. An important extension of models concerns considering of real space constrains like geomorphology, networks, and other natural structures. Recent developments in semi-supervised learning can improve modelling of environmental phenomena taking into account on geo-manifolds. An important part of the study deals with the analysis of relevant variables and models' inputs. This problem is approached by using different feature selection/feature extraction nonlinear tools. To demonstrate the application of machine learning algorithms several interesting case studies are considered: digital soil mapping using SVM, automatic mapping of soil and water system pollution using ANN; natural hazards risk analysis (avalanches, landslides), assessments of renewable resources (wind fields) with SVM and ANN models, etc. The dimensionality of spaces considered varies from 2 to more than 30. Figures 1, 2, 3 demonstrate some results of the studies and their outputs. Finally, the results of environmental mapping are discussed and compared with traditional models of geostatistics.

Phosphate and zinc transport and signalling in plants: toward a better understanding of their homeostasis interaction.

Inorganic phosphate (Pi) and zinc (Zn) are two essential nutrients for plant growth. In soils, these two minerals are either present in low amounts or are poorly available to plants. Consequently, worldwide agriculture has become dependent on external sources of Pi and Zn fertilizers to increase crop yields. However, this strategy is neither economically nor ecologically sustainable in the long term, particularly for Pi, which is a non-renewable resource. To date, research has emphasized the analysis of mineral nutrition considering each nutrient individually, and showed that Pi and Zn homeostasis is highly regulated in a complex process. Interestingly, numerous observations point to an unexpected interconnection between the homeostasis of the two nutrients. Nevertheless, despite their fundamental importance, the molecular bases and biological significance of these interactions remain largely unknown. Such interconnections can account for shortcomings of current agronomic models that typically focus on improving the assimilation of individual elements. Here, current knowledge on the regulation of the transport and signalling of Pi and Zn individually is reviewed, and then insights are provided on the recent progress made towards a better understanding of the Zn-Pi homeostasis interaction in plants.

Transgenic plant factories for the production of biopolymers and plateform chemicals

In the mid-to long-term, resource constraints will force society to cover a significant share of the future demand for fuels, materials and chemicals by renewable resources. This trend is already visible in the increasing conversion of carbohydrates and plant oils to fuels, chemicals, and polymers. In this perspective, we discuss current efforts and ideas to produce platform chemicals and polymers directly in transgenic plants.

Kernel-based Mapping of Meteorological Fields in Complex Orography

Due to the advances in sensor networks and remote sensing technologies, the acquisition and storage rates of meteorological and climatological data increases every day and ask for novel and efficient processing algorithms. A fundamental problem of data analysis and modeling is the spatial prediction of meteorological variables in complex orography, which serves among others to extended climatological analyses, for the assimilation of data into numerical weather prediction models, for preparing inputs to hydrological models and for real time monitoring and short-term forecasting of weather.In this thesis, a new framework for spatial estimation is proposed by taking advantage of a class of algorithms emerging from the statistical learning theory. Nonparametric kernel-based methods for nonlinear data classification, regression and target detection, known as support vector machines (SVM), are adapted for mapping of meteorological variables in complex orography.With the advent of high resolution digital elevation models, the field of spatial prediction met new horizons. In fact, by exploiting image processing tools along with physical heuristics, an incredible number of terrain features which account for the topographic conditions at multiple spatial scales can be extracted. Such features are highly relevant for the mapping of meteorological variables because they control a considerable part of the spatial variability of meteorological fields in the complex Alpine orography. For instance, patterns of orographic rainfall, wind speed and cold air pools are known to be correlated with particular terrain forms, e.g. convex/concave surfaces and upwind sides of mountain slopes.Kernel-based methods are employed to learn the nonlinear statistical dependence which links the multidimensional space of geographical and topographic explanatory variables to the variable of interest, that is the wind speed as measured at the weather stations or the occurrence of orographic rainfall patterns as extracted from sequences of radar images. Compared to low dimensional models integrating only the geographical coordinates, the proposed framework opens a way to regionalize meteorological variables which are multidimensional in nature and rarely show spatial auto-correlation in the original space making the use of classical geostatistics tangled.The challenges which are explored during the thesis are manifolds. First, the complexity of models is optimized to impose appropriate smoothness properties and reduce the impact of noisy measurements. Secondly, a multiple kernel extension of SVM is considered to select the multiscale features which explain most of the spatial variability of wind speed. Then, SVM target detection methods are implemented to describe the orographic conditions which cause persistent and stationary rainfall patterns. Finally, the optimal splitting of the data is studied to estimate realistic performances and confidence intervals characterizing the uncertainty of predictions.The resulting maps of average wind speeds find applications within renewable resources assessment and opens a route to decrease the temporal scale of analysis to meet hydrological requirements. Furthermore, the maps depicting the susceptibility to orographic rainfall enhancement can be used to improve current radar-based quantitative precipitation estimation and forecasting systems and to generate stochastic ensembles of precipitation fields conditioned upon the orography.

Production of renewable polymers from crop plants

Plants produce a range of biopolymers for purposes such as maintenance of structural integrity, carbon storage, and defense against pathogens and desiccation. Several of these natural polymers are used by humans as food and materials, and increasingly as an energy carrier. In this review, we focus on plant biopolymers that are used as materials in bulk applications, such as plastics and elastomers, in the context of depleting resources and climate change, and consider technical and scientific bottlenecks in the production of novel or improved materials in transgenic or alternative crop plants. The biopolymers discussed are natural rubber and several polymers that are not naturally produced in plants, such as polyhydroxyalkanoates, fibrous proteins and poly-amino acids. In addition, monomers or precursors for the chemical synthesis of biopolymers, such as 4-hydroxybenzoate, itaconic acid, fructose and sorbitol, are discussed briefly

Treatment of ruptured abdominal aortic aneurysm, a permanent challenge or a waste of resources? Prediction of outcome using a multi-organ-dysfunction score.

OBJECTIVES: in a retrospective study, attempts have been made to identify individual organ-dysfunction risk profiles influencing the outcome after surgery for ruptured abdominal aortic aneurysms. METHODS: out of 235 patients undergoing graft replacement for abdominal aortic aneurysms, 57 (53 men, four women, mean age 72 years [s.d. 8.8]) were treated for ruptured aneurysms in a 3-year period. Forty-eight preoperative, 13 intraoperative and 34 postoperative variables were evaluated statistically. A simple multi-organ dysfunction (MOD) score was adopted. RESULTS: the perioperative mortality was 32%. Three patients died intraoperatively, four within 48 h and 11 died later. A significant influence for pre-existing risk factors was identified only for cardiovascular diseases. Multiple linear-regression analysis indicated that a haemoglobin <90 g/l, systolic blood pressure <80 mmHg and ECG signs of ischaemia at admission were highly significant risk factors. The cause of death for patients, who died more than 48 h postoperatively, was mainly MOD. All patients with a MOD score >/=4 died (n=7). These patients required 27% of the intensive-care unit (ICU) days of all patients and 72% of the ICU days of the non-survivors. CONCLUSION: patients with ruptured aortic aneurysms from treatment should not be excluded. However, a physiological scoring system after 48 h appears justifiable in order to decide on the appropriateness of continual ICU support.

Country actions to meet UN commitments on non-communicable diseases: a stepwise approach.

Strong leadership from heads of state is needed to meet national commitments to the UN political declaration on non-communicable diseases (NCDs) and to achieve the goal of a 25% reduction in premature NCD mortality by 2025 (the 25 by 25 goal). A simple, phased, national response to the political declaration is suggested, with three key steps: planning, implementation, and accountability. Planning entails mobilisation of a multisectoral response to develop and support the national action plan, and to build human, financial, and regulatory capacity for change. Implementation of a few priority and feasible cost-effective interventions for the prevention and treatment of NCDs will achieve the 25 by 25 goal and will need only few additional financial resources. Accountability incorporates three dimensions: monitoring of progress, reviewing of progress, and appropriate responses to accelerate progress. A national NCD commission or equivalent, which is independent of government, is needed to ensure that all relevant stakeholders are held accountable for the UN commitments to NCDs.

The SIB Swiss Institute of Bioinformatics' resources: focus on curated databases.

The SIB Swiss Institute of Bioinformatics (www.isb-sib.ch) provides world-class bioinformatics databases, software tools, services and training to the international life science community in academia and industry. These solutions allow life scientists to turn the exponentially growing amount of data into knowledge. Here, we provide an overview of SIB's resources and competence areas, with a strong focus on curated databases and SIB's most popular and widely used resources. In particular, SIB's Bioinformatics resource portal ExPASy features over 150 resources, including UniProtKB/Swiss-Prot, ENZYME, PROSITE, neXtProt, STRING, UniCarbKB, SugarBindDB, SwissRegulon, EPD, arrayMap, Bgee, SWISS-MODEL Repository, OMA, OrthoDB and other databases, which are briefly described in this article.