ABSTRACT:This study aimed at quantifying carbon (C) and biomass stocks in shoot portion, leaf litter, roots and soil within a fragment of dense savanna 'cerradão', 158.5 ha in area, located in Minas Gerais state. Measures were quantified using dendrometric parameters obtained during the forest inventory and collection of leaf litter, root and soil samples. Furrows were dug in the soil each 100 cm long, 50 cm wide and 100 cm deep in order to collect root samples at depths of 0-30 cm, 30-50 cm and 50-100 cm, and soil samples from the layers 0-10 cm, 10-20 cm, 20-40 cm, 40-60 cm and 60-100 cm, as well as any leaf litter from the surrounding surface. Analyses were performed in the Organic Matter Study Laboratory (DCS/UFLA) to determine C contents in the above matrices, using an Elementar analyzer model Vario TOC Cube. Higher C contents and stocks and lower density were noted in topmost soil layers. In cerradão, shoot portion was found to be the matrix contributing the most to biomass production, followed by roots and leaf litter. Carbon stock in the fragment was 139.7 Mg ha -1 . Soil was the matrix contributing the most to stocked C (64.8%), followed by the shoot portion (26.3%), roots (5.2%) and leaf litter (3.7%).Key words: Forest inventory, carbon sequestration, cerrado, biomass, leaf litter. ESTOQUES DE CARBONO E BIOMASSA DE UM FRAGMENTO DE CERRADÃO EM MINAS GERAIS, BRASIL RESUMO: Este trabalho foi desenvolvido para quantificar o estoque de carbono (C) e biomassa presente na parte aérea lenhosa, serrapilheira, raízes e solos, num fragmento de cerradão com 158,5 ha, em Minas Gerais. As quantificações foram realizadas por meio de medidas dendrométricas tomadas durante o inventário florestal e de coleta de amostras de serrapilheira

Background: In fast-growing forests such as Eucalyptus plantations, the correct determination of stand productivity is essential to aid decision making processes and ensure the efficiency of the wood supply chain. In the past decade, advances in remote sensing and computational methods have yielded new tools, techniques, and technologies that have led to improvements in forest management and forest productivity assessments. Our aim was to estimate and map the basal area and volume of Eucalyptus stands through the integration of forest inventory, remote sensing, parametric, and nonparametric methods of spatial prediction. Methods: This study was conducted in 20 5-year-old clonal stands (362 ha) of Eucalyptus urophylla S.T.Blake x Eucalyptus camaldulensis Dehnh. The stands are located in the northwest region of Minas Gerais state, Brazil. Basal area and volume data were obtained from forest inventory operations carried out in the field. Spectral data were collected from a Landsat 5 TM satellite image, composed of spectral bands and vegetation indices. Multiple linear regression (MLR), random forest (RF), support vector machine (SVM), and artificial neural network (ANN) methods were used for basal area and volume estimation. Using ordinary kriging, we spatialised the residuals generated by the spatial prediction methods for the correction of trends in the estimates and more detailing of the spatial behaviour of basal area and volume. Results: The ND54 index was the spectral variable that had the best correlation values with basal area (r = − 0.91) and volume (r = − 0.52) and was also the variable that most contributed to basal area and volume estimates by the MLR and RF methods. The RF algorithm presented smaller basal area and volume errors when compared to other machine learning algorithms and MLR. The addition of residual kriging in spatial prediction methods did not necessarily result in relative improvements in the estimations of these methods. Conclusions: Random forest was the best method of spatial prediction and mapping of basal area and volume in the study area. The combination of spatial prediction methods with residual kriging did not result in relative improvement of spatial prediction accuracy of basal area and volume in all methods assessed in this study, and there is not always a spatial dependency structure in the residuals of a spatial prediction method. The approaches used in this study provide a framework for integrating field and multispectral data, highlighting methods that greatly improve spatial prediction of basal area and volume estimation in Eucalyptus stands. This has potential to support fast growth plantation monitoring, offering options for a robust analysis of high-dimensional data.

Change detection methods are often incapable of accurately detecting changes within time series that are heavily influenced by seasonal variations. Techniques for de-seasoning time series or methods that apply the spatial context have been used to improve the results of change detection. However, few studies have explored Landsat’s shortwave infrared channel (SWIR 2) to discriminate between seasonal changes and land use/land cover changes (LULCC). Here, we explored the effectiveness of Operational Land Imager (OLI) spectral bands and vegetation indices for detecting deforestation in highly seasonal areas of Brazilian savannas. We adopted object-based image analysis (OBIA), applying a multidate segmentation to an OLI time series to generate input data for discrimination of deforestation from seasonal changes using the Random Forest (RF) algorithm. We found adequate separability between deforested objects and seasonal changes using SWIR 2. Using spectral indices computed from SWIR 2, the RF algorithm generated a change map with an overall accuracy of 88.3%. For deforestation, the producer’s accuracy was 88.0% and the user’s accuracy was 84.6%. The SWIR 2 channel as well as the mid-infrared burn index presented the highest importance among spectral variables computed by the RF average impurity decrease measure. Our results give support to further change detection studies regarding to suitable spectral channels and provided a useful foundation for savanna change detection using an object-based method applied to Landsat time series.

RESUMOObjetivou-se avaliar e aplicar as redes neurais artificias (RNA) para estimar o diâmetro (di) ao longo do fuste (hi) em um plantio de Eucalyptus sp., e com isso comparar com o método de regressão linear por um polinômio do quinto grau (PQG). Foram cubadas 74 árvores pelo método absoluto e destrutivo, coletando diâmetros (di) a várias alturas (hi). Para realizar a modelagem de predição dos diâmetros, a base de dados foi dividida em um conjunto de treinamento e outro de teste. O PQG foi ajustado por meio do software estatístico R considerando o método dos mínimos quadrados ordinários como procedimento de ajuste. As variáveis utilizadas para estimar os diâmetros (di) das árvores pelo método do PQG foram: Dap (diâmetro a 1,30m), di, hi e Ht (altura total). A RNA do tipo perceptron de múltiplas camadas foi implementada no software Scilab com o auxílio do ANN toolbox. As variáveis utilizadas para o treinamento da RNA foram obtidas por meio de combinações com diferentes operações matemáticas nos dados de Dap, hi e Ht. As estatísticas MAPE, MAD, MSD, RSME (%) foram aplicadas nos dados estimados com a finalidade de analisar os desvios frente aos dados observados e realizar a comparação entre os métodos utilizados. Considerando uma comparação aplicada dos métodos, foi calculado o volume e a quantificação do sortimento por árvore, usando como base as estimativas geradas. A RNA em geral apresentou boas estatísticas e um melhor gráfico residual. Conclui-se que ambas as metodologias mostraram-se eficientes para alcançar os objetivos propostos, assim as RNA podem ser consideradas como uma boa alternativa de uso e aplicação. PALAVRAS-CHAVE: Afilamento, Inteligência Artificial. Manejo florestal ENCICLOPÉDIA BIOSFERA, Centro Científico Conhecer -Goiânia, v.11 n.22; p. 2015 2420 FORECAST DIAMETERS ALONG THE STEM BY ARTIFICIAL NEURAL NETWORKSABSTRACT This study aimed apply and evaluate the artificial neural networks (ANN) to estimate the diameter (di) along the stem (hi) in a plantation of Eucalyptus sp., and after compare with the linear regression method for the fifth polynomial degree (QGP). Seventy four trees were cubed by the absolute and destructive method. The diameters (di) were collect at different heights (hi). To model the prediction of diameters, was necessary divided the database into a training set and other for test We adjusted the QGP and used the statistical software R considering the method of ordinary least squares as adjustment procedures. The variables used to model by regression QPG were: Dap (diameter 1,30m), di, hi and Ht (overall height). The ANN perceptron type multilayer was implemented in Scilab software with the help of ANN toolbox. The variables used for the training of ANN were obtained by an combinations with different mathematical operations on data Dap, hi and Ht.The statistics, MAP,MAD, MSD, RSME (%) were applied on the estimated data for the purpose of analyzing the deviations compared to the observed data and compare the methods used. Considering a apply comparison of the methods, the volum...

RESUMOOs impactos gerados na paisagem após a colheita florestal em reflorestamentos são visíveis, porém, o corte raso é um processo necessário para garantir uma produção sustentada e introduzir novas tecnologias. Uma alternativa de controle é utilizar restrições de adjacência nos modelos matemáticos. Assim, o objetivo do estudo foi avaliar a capacidade da meta-heurística SA na resolução de modelos matemáticos com restrições de adjacência do tipo URM, e observar sua ação com o aumento da complexidade do problema. O estudo foi conduzido em um projeto florestal contendo 52 talhões, sendo criados 8 cenários, onde o modelo I de Johnson e Scheurmann (1977) foi usado como referência. A restrição de adjacência do tipo URM foi usada para controlar o corte de talhões adjacentes. Os modelos foram resolvidos pela PLI e meta-heurística SA, no qual foi processada 100 vezes/cenário. Os resultados mostraram que o cenário 8 consumiu 137.530 segundos via PLI, gastando um tempo de 2.023,09 vezes a mais que o tempo médio de processamento da metaheurística SA (67,98 segundos). As melhores soluções ficaram 4,71 % (cenário 1) a 11,40 % (cenário 8) distante do ótimo (PLI). A meta-heurística SA é capaz de resolver o problema florestal, atendendo às metas na maioria das vezes. O aumento da complexidade produz um maior desvio em relação ao ótimo. Concluise que a meta-heurística SA não deve ser processada uma única vez, pois há riscos de se obter soluções inferiores, caso seja feita, deve-se aumentar o tempo de parada. Palavras-chave: inteligência artificial; programação linear inteira; colheita florestal. ABSTRACTThe impacts on the landscape after forest harvesting in reforestation are visible, but the cutting is a necessary process to ensure a sustained yield and introduce new technologies. An alternative of control is to use the adjacency constraints in the mathematical models. Thus, the aim of the study was to assess the ability of the metaheuristic SA to solve mathematical models with adjacency constraints type URM, and to check its action with the increasing of the problem complexity. The study was conducted in a forest project containing 52 stands, and created 8 scenarios, where the Johnson and Scheurmann (1977) model I was used as reference. The adjacency constraint type URM was used to control the cutting of adjacent stands. The models were solved by the ILP and metaheuristic SA, which was sued 100 times per scenario. The results showed that the scenario 8 has consumed 137,530 seconds via PLI, which represented 2,023.09 times more than the average time processing of the SA metaheuristic (67.98 seconds). The best solutions were 4.71 % (scenario 1) to 11.40 % (scenario 8) far from the optimal (ILP). The metaheuristic SA is capable to solve the forest problem, meeting the targets in the most cases. The increasing of complexity produced a higher deviation from the optimal. Concludes that the metaheuristic SA should not be processed a single time, because there are hazards in obtain inferior solutions, but doing it is recommended to in...