Browsing by Author "Taboada, Javier"
Now showing 1 - 10 of 15
Results Per Page
Sort Options
- Aplicación de redes neuronales en la determinación de origen botánico de miel a partir de sus propiedades físico-químicasPublication . Iglesias, Carla; Anjos, O.; Martínez, Javier; Peres, Maria de Fátima; García, Ángela; Taboada, JavierAplicación de redes neuronales en la determinación de origen botánico de miel a partir de sus propiedades físico-químicas.
- Developing a new bayesian risk index for risk evaluation of soil contaminationPublication . Albuquerque, M.T.D.; Gerassis, Saki; Sierra, C.; Taboada, Javier; Martín, José; Antunes, I.M.H.R.; Gallego, J.R.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.
- Future habitat suitability for species under climate change: lessons learned from the strawberry tree case studyPublication . Gerassis, Saki; Albuquerque, M.T.D; Roque, Natália; Ribeiro, Sílvia; Taboada, Javier; Ribeiro, M.M.A.Climate change is already a reality, and habitat loss is affecting relentlessly tree species distributions. The strawberry tree (Arbutus unedo L., Ericaceae) is a Mediterranean evergreen tree used in this article as a case study to evince its expected threatening situation in the upcoming age. This research work seeks to identify the bioclimatic and physiographic variables that have the most impact on the strawberry tree’s spatial distribution in Portugal, acquiring vital knowledge for the design of accurate conservation and afforestation plans for the use and conservation of strawberry tree, working as a guide under a climate change scenario. For that, twenty-one bioclimatic variables, two physiographic attributes (altitude and slope), and the Emberger Index (EI) were used together with 318 observations of strawberry trees, to build a scalable Bayesian procedure, based on machine learning techniques, aimed to assess the species’ future habitat evolution through three temporal scenarios: (i) Control Run (1960–1990); (ii) 2050 and (iii) 2070. The results indicate for 2050 a 30% loss of the humid subregion and a 35% increase in the semi-arid sub-region towards the north. In 2070, it is expected a 2% recuperation for the sub-humid area, but an 8% loss of the humid sub-area. Under these extreme climate change conditions, it is anticipated an almost complete loss of habitat for the strawberry tree in the south of Portugal. The expected ecological evolvability may trigger future migration paths and new refuges’ settlement in the northern sub-region for the succeeding decades and suggesting after 2070 the possibility of habitat switch and species drifting.
- Herramientas SIG para el analisis espacial de la vulnerabilidad de un acuiferoPublication . Sanz-Lobón, Germán; Martínez-Alegría, Roberto; Albuquerque, M.T.D.; Taboada, Javier; Antunes, I.M.H.R.Herramientas SIG para el analisis espacial de la vulnerabilidad de un acuifero.
- Hydrogeological vulnerability assessment in urban systems, SpainPublication . Sanz-Lobón, Germán; Albuquerque, M.T.D.; Martinez-Alegría, Roberto; Antunes, I.M.H.R.; Taboada, JavierThe main objective of this research is the study of vulnerability to pollution in an unconfined karstic aquifer system. Aquifer vulnerability assessment to define critical zones of contamination is a core issue an effective monitoring network for groundwater management. Vulnerability integration is addressed for risk valuation and risk–benefit considerations, focusing the requirements of the European Community’s Water and Groundwater Directives. The development of an integrated vulnerability assessment methodology can be useful for the effective management and protection of this valuable freshwater source. The research insights suggest that an effective governance is mandatory as the future highway, the prison and the airport are overlaying the aquifer’s most vulnerable areas.
- Local versus regional soil screening levels to identify potentially polluted areasPublication . Boente, Carlos; Gerassis, Saki; Albuquerque, M.T.D.; Taboada, Javier; Gallego, J.R.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.
- Mapping occupational health risk factors in the primary sector: a novel supervised machine learning and area-to-point poisson kriging approachPublication . Gerassis, Saki; Boente, Carlos; Albuquerque, M.T.D.; Ribeiro, M.M.A.; Abad, A.; Taboada, JavierWorkers 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.
- Modelação ecológica em medronheiro usando redes BaiesianasPublication . Albuquerque, M.T.D.; Gerassis, Saki; Roque, Natália; Ribeiro, Sílvia; Taboada, Javier; Martín, José; Ribeiro, M.M.A.O medronheiro (Arbutus unedo L.) tem potencial para ser uma cultura de sucesso comercial em várias regiões de Portugal, onde está bem-adaptado ao clima e solos. A espécie tem sido usada pelas populações locais para consumo do fruto em fresco ou processado, sobretudo como aguardente, no entanto continua a ser uma espécie largamente negligenciada, ainda que tenha muitos usos comerciais possíveis, desde a produção do fruto em fresco ou processado, a uso ornamental, farmacêutico, ou aplicações dos produtos bioativos. Além disso, devido ao seu estatuto pioneiro, é útil na recuperação dos solos, evitando a desertificação e tem, também, resistência ao fogo. A construção de um modelo ecológico para o medronho, foi obtida através de uma abordagem Baiesiana. Na investigação em curso, foi utilizada uma grelha de 1 Km2 ao longo de todo o território português (90425 parcelas), para o conjunto dos 10 atributos utilizados: sete variáveis bioclimáticas para a representação de uma "distância climática" - Bio1; Bio2; Bio5; Bio 9; Bio 15; Temperatura Máxima e Temperatura Mínima (WorldClim 1.4, 2017) e três variáveis geográficas - Altitude; Declive e Uso do Solo - para capturar uma "distância geográfica". Finalmente, a presença/ausência da espécie foi a variável objetivo. Foram usados quatro cenários: 1. Série de controle (1960-1990), visando a modelação das condições atuais; 2. Três diferentes cenários de efeito de estufa: Holocénico Médio (há 6000 anos); 2050 e 2070, utilizando o cenário de concentração de CO2 mais pessimista (RCP 8,5). As redes Baiesianas são Grafos Acíclicos Direcionados (GAD) onde os nós e os arcos tipificam as relações de causa e efeito entre variáveis em estudo. A estrutura topológica de um modelo Baiesiano reflete a dependência das variáveis e descreve a distribuição de probabilidade de certos acontecimentos, ocorrendo a condições específicas. As informações obtidas neste estudo serão utilizadas para a elaboração de regiões de proveniência, para melhoramento genético e conservação da espécie.
- Neural networks applied to discriminate botanical origin of honeysPublication . Anjos, Ofélia; Iglesias, Carla; Peres, Maria de Fátima; Martínez, Javier; García, Ángela; Taboada, JavierThe 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.
- Prediction of mechanical strength of cork under compression using machine learning techniquesPublication . García, Ángela; Anjos, O.; Iglesias, Carla; Pereira, Helena; Martínez, Javier; Taboada, JavierIn 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.