Mapeamento digital de solos com base na extrapolação de mapas entre áreas fisiograficamente semelhantes

O objetivo deste trabalho foi testar metodologias de mapeamento digital de solos (MDS) e avaliar a possibilidade de extrapolação de mapas entre áreas fisiograficamente semelhantes. A área de referência para o treinamento do modelo localizou-se no Município de Sentinela do Sul, RS, e a extrapolação foi feita para o Município Cerro Grande do Sul, RS. Desenvolveram-se pelo MDS modelos com o uso de variáveis ambientais, como preditoras, e as classes de solos - obtidas de um levantamento convencional na escala 1:50.000 - como variáveis dependentes. Testou-se o uso combinado de dois modelos de árvore de decisão (AD), treinados em duas paisagens com diferentes classes de drenagem. Para Sentinela do Sul, a concordância dos mapas preditos com os produzidos pelo levantamento convencional foi avaliada por matrizes de erro. Como a importância dos erros de mapeamento é variável, criou-se uma matriz ponderada, para atribuir diferentes importâncias aos erros específicos de mapeamento entre as distintas unidades de mapeamento. A acurácia do mapa de Cerro Grande do Sul foi avaliada pela verdade de campo. A extrapolação dos mapas gera resultados satisfatórios, com acurácia maior do que 75%. O uso de modelos com duas AD separadas por paisagens homogêneas gera mapas extrapolados com maior acurácia, avaliada pela verdade de campo.

Redes neurais artificiais para a modelagem do volume de madeira e biomassa do cerradão com dados de satélite

Resumo:O objetivo deste trabalho foi avaliar a eficácia da aplicação de modelos de análise de regressão e redes neurais artificiais (RNAs) na predição do volume de madeira e da biomassa acima do solo, da vegetação arbórea em área de cerradão. Volume de madeira e biomassa foram estimados com equações alométricas desenvolvidas para a área de estudo. Os índices de vegetação, como variáveis preditoras, foram estimados a partir de imagens do sensor LISS-III, e a área basal foi determinada por medições na floresta. A precisão das equações foi verificada pela correlação entre os valores estimados e observados (r), erro-padrão da estimativa (Syx) e gráfico residual. As equações de regressão para o volume de madeira total e do fuste (0,96 e 0,97 para r, e 11,92 e 9,72% para Syx, respectivamente) e para a biomassa (0,91 e 0,92 para r, e 22,73 e 16,80% para Syx, respectivamente) apresentaram bons ajustes. As redes neurais também apresentaram bom ajuste com o volume de madeira (0,99 e 0,99 para r, e 4,93 e 4,83% para Syx) e a biomassa (0,97 e 0,98 r, e 8,92 e 7,96% para Syx, respectivamente). A área basal e os índices de vegetação foram eficazes na estimativa do volume de madeira e biomassa para o cerradão. Os valores reais de volume de madeira e biomassa não diferiram estatisticamente dos valores estimados pelos modelos de regressão e redes neurais (χ2ns); contudo, as RNAs são mais acuradas.

Redes neurais artificiais para identificar genótipos de feijão-caupi semiprostrado com alta adaptabilidade e estabilidade fenotípicas

Resumo: O objetivo deste trabalho foi verificar a concordância entre as redes neurais artificiais (RNAs) e o método de Eberhart & Russel na identificação de genótipos de feijão-caupi (Vigna unguiculata) com alta adaptabilidade e estabilidade fenotípicas. Utilizou-se o delineamento experimental de blocos ao acaso com quatro repetições. Os tratamentos consistiram de 18 linhagens experimentais e duas cultivares de feijão-caupi. Foram conduzidos quatro ensaios de valor de cultivo e uso nos municípios de Aquidauana, Chapadão do Sul e Dourados, no estado do Mato Grosso do Sul. Os dados de produtividade de grãos foram submetidos às análises de variância individual e conjunta. Em seguida, os dados foram submetidos às análises de adaptabilidade e estabilidade por meio dos métodos de Eberhart & Russell e de RNAs. Houve elevada concordância entre os métodos avaliados quanto à discriminação da adaptabilidade fenotípica dos genótipos de feijão-caupi semiprostrado, o que indica que as RNAs podem ser utilizadas em programas de melhoramento genético. Em ambos os métodos avaliados, os genótipos BRS Xiquexique, TE97-304G-12 e MNC99-542F-5 são recomendados para ambientes desfavoráveis, gerais e favoráveis, respectivamente, por apresentarem produtividade de grãos acima da média geral dos ambientes e alta estabilidade fenotípica.

Redes neurais e suas aplicações em calibração multivariada

Neural Networks are a set of mathematical methods and computer programs designed to simulate the information process and the knowledge acquisition of the human brain. In last years its application in chemistry is increasing significantly, due the special characteristics for model complex systems. The basic principles of two types of neural networks, the multi-layer perceptrons and radial basis functions, are introduced, as well as, a pruning approach to architecture optimization. Two analytical applications based on near infrared spectroscopy are presented, the first one for determination of nitrogen content in wheat leaves using multi-layer perceptrons networks and second one for determination of BRIX in sugar cane juices using radial basis functions networks.

Estudo do estado fundamental de aglomerados de silício via redes neurais

We introduce a global optimization method based on the cooperation between an Artificial Neural Net (ANN) and Genetic Algorithm (GA). We have used ANN to select the initial population for the GA. We have tested the new method to predict the ground-state geometry of silicon clusters. We have described the clusters as a piling of plane structures. We have trained three ANN architectures and compared their results with those of pure GA. ANN strongly reduces the total computational time. For Si10, it gained a factor of 5 in search speed. This method can be easily extended to other optimization problems.

Desempenho físico-químico de metais e estruturas de concreto de redes de distribuição de energia: estudo de caso na região de Manaus

The influence of natural aging furthered by atmospheric corrosion of parts of electric transformers and materials, as well as of concrete poles and cross arms containing corrosion inhibitors was evaluated in Manaus. Results for painted materials, it could showed that loss of specular gloss was more intensive in aliphatic polyurethane points than in acrylic polyurethane ones. No corrosion was observed for metal and concrete samples until 400 days of natural aging. Corrosion in steel reinforcement was noticed in some poles, arising from manufacturing faults, such as low cement content, water/cement ratio, thin concrete cover thickness, etc. The performance of corrosion inhibitors was assessed by many techniques after natural and accelerated aging in a 3.5% saline aqueous solution. The results show the need for better chemical component selection and its concentration in the concrete mixture.

A tabela periódica dos elementos químicos prevista por redes neurais artificiais de Kohonen

Although several chemical elements were not known by end of the 18th century, Mendeleyev came up with an astonishing achievement: the periodic table of elements. He was not only able to predict the existence of (then) new elements but also to provide accurate estimates of their chemical and physical properties. This is certainly a relevant example of the human intelligence. Here, we intend to shed some light on the following question: Can an artificial intelligence system yield a classification of the elements that resembles, in some sense, the periodic table? To achieve our goal, we have fed a self-organized map (SOM) with information available at Mendeleyev's time. Our results show that similar elements tend to form individual clusters. Thus, SOM generates clusters of halogens, alkaline metals and transition metals that show a similarity with the periodic table of elements.

QuEChERS: um método moderno de preparo de amostra para determinação multirresíduo de pesticidas em alimentos por métodos cromatográficos acoplados à espectrometria de massas

This review attempts to provide an updated overview of the Quick, Easy, Cheap, Effective, Ruged and Safe (QuEChERS) multiresidue extraction method, that involves initial extraction in acetonitrile, an extraction/partition step after the addition of salt, and a cleanup step utilizing dispersive solid phase extraction. QuEChERS method is nowadays the most applied extraction method for the determination of pesticide residues in food samples, providing acceptable recoveries for acidic, neutral and basic pesticides. Several applications for various food matrices (fruits, vegetables, cereals and others) in combination with chromatographic mass spectrometry analysis were presented.

Aplicação de redes neurais artificiais na identificação de gasolinas adulteradas comercializadas na região de Londrina - Paraná

The multilayer perceptron network was used to classify the gasoline. The main parameters used in the classification were established by the Ordinance nº 309 of the Agência Nacional do Petróleo, but without informing the network the legal limits of these parameters. The network used had 10 neurons in a single hidden layer, learning rate of 0.04 and 250 training epochs. The application of artificial neural network served classify 100% of the commercialized gas in the region of Londrina-PR and to identify the tampered gasoline even those suspected of tampering.

Determinação de constituintes químicos em madeira de eucalipto por Pi-CG/EM e calibração multivariada: comparação entre redes neurais artificiais e máquinas de vetor suporte

Multivariate models were developed using Artificial Neural Network (ANN) and Least Square - Support Vector Machines (LS-SVM) for estimating lignin siringyl/guaiacyl ratio and the contents of cellulose, hemicelluloses and lignin in eucalyptus wood by pyrolysis associated to gaseous chromatography and mass spectrometry (Py-GC/MS). The results obtained by two calibration methods were in agreement with those of reference methods. However a comparison indicated that the LS-SVM model presented better predictive capacity for the cellulose and lignin contents, while the ANN model presented was more adequate for estimating the hemicelluloses content and lignin siringyl/guaiacyl ratio.

Uso de redes neurais recorrentes na determinação das constantes de acidez para a 7-epiclusianona em misturas etanol-água

This work propose a recursive neural network to solve inverse equilibrium problem. The acidity constants of 7-epiclusianone in ethanol-water binary mixtures were determined from multiwavelength spectrophotmetric data. A linear relationship between acidity constants and the %w/v of ethanol in the solvent mixture was observed. The proposed method efficiency is compared with the Simplex method, commonly used in nonlinear optimization techniques. The neural network method is simple, numerically stable and has a broad range of applicability.

Redes de colaboração científica na área de química no Brasil: um estudo baseado nas coautorias dos artigos da revista Química Nova

In this paper we built three co-authorship networks displaying the acquaintances between countries, universities and authors that have published papers in Quimica Nova from 1995 to 2008. Our research was conducted applying a bibliometric approach to 1782 papers and over 4200 authors. Centrality measures were used and the most significant actors of each network were pointed out. The results using the centrality metrics and the network structures indicated that Quimica Nova resembles a typical scientific community.

Redes metalorgânicas e suas aplicações em catálise

Metal-organic frameworks (MOFs) form a new class of materials with well-defined yet tunable properties. These are crystalline, highly porous and exhibit strong metal-ligand interactions. Importantly, their physical and chemical properties, including pore size, pore structure, acidity, and magnetic and optical characteristics, can be tailored by choosing the appropriate ligands and metal precursors. Here we review the key aspects of synthesis and characterization of MOFs, focusing on lanthanide-based and vanadium-based materials. We also outline some of their applications in catalysis and materials science.

Mapas conceptuales como herramienta pedagógica en la enseñanza de la química orgánica

Organic Chemistry is a branch of Chemistry involving the study of the carbon atom, its compounds and reactions. Numerous investigations carried out in the field of teaching and learning processes indicate that knowledge of a conceptual and explanatory type is not conveyed in a conventional manner, but rather each individual is constructed. Therefore, the proposal for this study was devised to help students achieve significant sustainable learning in the area of reactivity in organic chemistry, using the Concept Maps described by Novak (1998) as a teaching tool.

REDUÇÃO DE VARIÁVEIS DE ENTRADA DE REDES NEURAIS ARTIFICIAIS A PARTIR DE DADOS DE ANÁLISE DE COMPONENTES PRINCIPAIS NA MODELAGEM DE OXIGÊNIO DISSOLVIDO

The objective of this work is to demonstrate the efficient utilization of the Principal Components Analysis (PCA) as a method to pre-process the original multivariate data, that is rewrite in a new matrix with principal components sorted by it's accumulated variance. The Artificial Neural Network (ANN) with backpropagation algorithm is trained, using this pre-processed data set derived from the PCA method, representing 90.02% of accumulated variance of the original data, as input. The training goal is modeling Dissolved Oxygen using information of other physical and chemical parameters. The water samples used in the experiments are gathered from the Paraíba do Sul River in São Paulo State, Brazil. The smallest Mean Square Errors (MSE) is used to compare the results of the different architectures and choose the best. The utilization of this method allowed the reduction of more than 20% of the input data, which contributed directly for the shorting time and computational effort in the ANN training.