Search results

A tool to predict the tensile properties of cork was applied in order to be used for material and application selection. The mechanical behaviour of cork under tensile stress was determined in the tangential and axial direction. Cork planks of two commercial quality classes were used and samples were taken at three radial positions in the planks.For the construction of the predictive model, nine properties were measured: mechanical properties (Young’s modulus, fracture stress and fracture strain) and the physical properties (porosity, number of pores, density, approximation of the pores to elliptical and circular shape and distance to the nearest pore). The aim of this research work was to predict the mechanical properties from the physical properties using neural networks.Initially, the problem was approached as a regression problem, but the poor correlation coefficients obtained made the authors define a classification problem. The criterion used for the classification problem was the test error rate, training the neural network with a variety of neurons in the hidden layer until the minimum error was achieved. The influence of each individual variable was also studied in order to evaluate their importance for the prediction of the mechanical properties.The results show that the Young’s modulus and fracture stress can be predicted with an error rate in test of 10.6 and 10.2 %, respectively, being the measure of the approximation of the pores to elliptical shape avoidable. Regarding the fracture strain, its prediction from physical properties implies an excessive error.

Resumen: En este trabajo se presenta el balance hídrico de una masa de agua subterránea de naturaleza kárstica de la cuenca sedimentaria del Duero, centro oeste de España. Los datos obtenidos para la realización del balance han sido introducidos en una herramienta de simulación con el fin de conocer la evolución temporal de los recursos hídricos a lo largo del año hidrológico. Para ello se ha sido necesario recurrir a la utilización de técnicas geostadísticas y el programa Visual Modflow. La masa de agua de los Montes Torozos se trata de un acuífero kárstico libre y colgado de origen sedimentario, y su balance está determinado por las precipitaciones y por el drenaje.

Este artigo deriva de uma comunicação apresentada em International workshop “Uranium, Environment and Public Health”

Só está disponível o resumo.

Resumo alargado da comunicação oral apresentada na 6th International Conference on Environmental Science and Development.

Só está disponível o resumo.

Industrial and agricultural activities heavily constrain soil quality. Potentially Toxic Elements (PTEs) are a threat to public health and the environment alike. In this regard, the identification of areas that require remediation is crucial. In the herein research a geochemical dataset (230 samples) comprising 14 elements (Cu, Pb, Zn, Ag, Ni, Mn, Fe, As, Cd, V, Cr, Ti, Al and S) was gathered throughout eight different zones distinguished by their main activity, namely, recreational, agriculture/livestock and heavy industry in the Avilés Estuary (North of Spain). Then a stratified systematic sampling method was used at short, medium, and long distances from each zone to obtain a representative picture of the total variability of the selected attributes. The information was then combined in four risk classes (Low, Moderate, High, Remediation) following reference values from several sediment quality guidelines (SQGs). A Bayesian analysis, inferred for each zone, allowed the characterization of PTEs correlations, the unsupervised learning network technique proving to be the best fit. Based on the Bayesian network structure obtained, Pb, As and Mn were selected as key contamination parameters. For these 3 elements, the conditional probability obtained was allocated to each observed point, and a simple, direct index (Bayesian Risk Index-BRI) was constructed as a linear rating of the pre-defined risk classes weighted by the previously obtained probability. Finally, the BRI underwent geostatistical modeling. One hundred Sequential Gaussian Simulations (SGS) were computed. The Mean Image and the Standard Deviation maps were obtained, allowing the definition of High/Low risk clusters (Local G clustering) and the computation of spatial uncertainty. High-risk clusters are mainly distributed within the area with the highest altitude (agriculture/livestock) showing an associated low spatial uncertainty, clearly indicating the need for remediation. Atmospheric emissions, mainly derived from the metallurgical industry, contribute to soil contamination by PTEs.

In this study, the accuracy of mathematical techniques such as multiple linear regression, clustering, decision trees (CART) and neural networks was evaluated to predict Young’s modulus, compressive stress at 30% strain and instantaneous recovery velocity of cork. Physical properties, namely test direction, density, porosity and pore number, as well as test direction were used as input. The better model was achieved when a classification problem was performed. Only compressive stress at 30% strain can be predicted with neural networks with an error rate of about 20%. The prediction of Young’s modulus and instantaneous recovery velocity led to unacceptably high error rates due to the heterogeneity of the material.

The aim of this work is develop a tool based on neural networks to predict the botanical origin of honeys using physical and chemical parameters. The managed database consists of 49 honey samples of 2 different classes: monofloral (almond, holm oak, sweet chestnut, eucalyptus, orange, rosemary, lavender, strawberry trees, thyme, heather, sunflower) and multifloral. The moisture content, electrical conductivity, water activity, ashes content, pH, free acidity, colorimetric coordinates in CIELAB space (L(∗), a(∗), b(∗)) and total phenols content of the honey samples were evaluated. Those properties were considered as input variables of the predictive model. The neural network is optimised through several tests with different numbers of neurons in the hidden layer and also with different input variables. The reduced error rates (5%) allow us to conclude that the botanical origin of honey can be reliably and quickly known from the colorimetric information and the electrical conductivity of honey.

Soil screening levels (SSLs) are reference threshold values required by environmental laws, established based on soil geochemical background data from often-extensive sampling areas. Such areas are often inappropriate for interpreting the true risk of pollution in small areas, since they overlook local factors (e.g., geology, industry, and traffic), which are unfeasible to encompass in large-scale samplings. To solve this issue, the calculation of local SSLs is proposed herein, performed on amajor scale closer to the area of interest. To exemplify this proposal, a soil sampling campaign was performed in the Municipality of Langreo, one of the most industrialized areas in the Principality of Asturias (northwestern Spain). Sampling allowed the measurement of local soil screening levels for several inorganic contaminants. Afterwards, a soil pollution index was calculated, referred to both regional and local thresholds, to assess the degree of contamination. Both pollution indicators were subjected to a methodology based on a Bayesian network analysis, followed by a stochastic sequential Gaussian simulation approach. The methodologies used showed differences in the identification of potentially polluted areas depending on the soil screening levels (regional or local) used. It was concluded that, in urban/industrial cores, local soil screening levels facilitate the identification of polluted areas and also reduce the uncertainty associated with sampling density and diffuse contamination. Thus, the use of local levels circumvents false-positive areas that would be classified as polluted were regional soil screening levels to be used.

A probabilistic Structural Equation Model (SEM) based on a Bayesian network construction is introduced to perform effective safety assessments for technicians and managers working on-site. Using novel AI software, the introduced methodology aims to show how to deal with complex scenarios in blasting operations, where typologically different variables are involved. Sequential Bayesian networks, learned from the data, were developed while variables were grouped into different clusters, representing related risks. From each cluster, a latent variable is induced giving rise to a final Bayesian network where cause and effect relationships maximize the prediction of the accident type. This hierarchical structure allows to evaluate different operational strategies, as well as analyze using information theory the weight of the different risk groups. The results obtained unveil hidden patterns in the occurrence of accidents due to flyrock phenomena regarding the explosive employed or the work characteristics. The integration of latent class clustering in the process proves to be an effective safeguard to categorize the variable of interest outside of personal cognitive biases. Finally, the model design and the software applied to show a flexible workflow, where workers at different corporate levels can feel engaged to try their beliefs to design safety interventions.

Workers around the world spend nearly a quarter of their time at work Occupational health is gaining great importance due to the profound impact on people long term health. The health status of the primary sector workforce is a great unknown for medical geography where health maps and spatial patterns have not been able to explain years of changing disease rates. This article proposes a new approach based on a solid characterization of the health status, which is the target node of an information theory-based Bayesian network machine-learnt from 13,000 medical examinations undertook to rural workers in Spain between 2012 and 2016. From the main health risks identified, a supervised binary logistic regression is used to produce a classification of adverse medical conditions giving rise to not healthy workers. Finally, Area-to-Point Poisson kriging is computed to provide a spatial analysis representing the incidence rate and spatial patterns of the main adverse medical conditions over the Spanish territory. The study illustrates how to overcome the challenges of working with discrete occupational data. Conceptually, high cholesterol and high glucose can be pinpointed with accuracy as the two main health risks for the working population in the primary sector.