Deforestation is one of the major threats to natural ecosystems. This process has a substantial contribution to climate change and biodiversity reduction. Therefore, the monitoring and early detection of deforestation is an essential process for preservation. Techniques based on satellite images are among the most attractive options for this application. However, many approaches involve some human intervention or are dependent on a manually selected threshold to identify regions that suffer deforestation. Motivated by this scenario, the present work evaluates Deep Learning-based strategies for automatic deforestation detection, namely, Early Fusion (EF), Siamese Network (SN), and Convolutional Support Vector Machine (CSVM) as well as Support Vector Machine (SVM), used as the baseline. The target areas are two regions with different deforestation patterns: the Amazon and Cerrado biomes in Brazil. The experiments used two co-registered Landsat 8 images acquired at different dates. The strategies based on Deep Learning achieved the best performance in our analysis in comparison with the baseline, with SN and EF superior to CSVM and SVM. In the same way, a reduction of the salt-and-pepper effect in the generated probabilistic change maps was noticed as the number of training samples increased. Finally, the work assesses how the methods can reduce the time invested in the visual inspection of deforested areas.

The Santa Catarina Southern Plateau is located in Southern Brazil and is a region that has gained considerable attention due to the rapid conversion of the typical landscape of natural grasslands and wetlands into agriculture, reforestation, pasture, and more recently, wind farms. This study’s main goal was to characterize the polarimetric attributes of the experimental quad-polarization acquisition mode of the Advanced Land Observing Satellite/Phased Array type L-band Synthetic Aperture Radar (ALOS/PALSAR-2) for mapping seven land cover classes. The polarimetric attributes were evaluated alone and combined with SENTINEL-2A using a supervised classification method based on the Support Vector Machine (SVM) algorithm. The results showed that the intensity backscattering alone reached an overall classification accuracy of 37.48% and a Kappa index of 0.26. Interestingly, the addition of polarimetric features increased to 71.35% and 0.66, respectively. It shows that the use of polarimetric decomposition features was relatively efficient in discriminating land cover classes. SENTINEL-2A data alone performed better and achieved a weighted overall accuracy and Kappa index of 85.56% and 0.82. This increase was also significant for the Z-test. However, the addition of ALOS/PALSAR-2 derived features to SENTINEL-2A slightly improved accuracy and was marginally significant at a 95% confidence level only when all features were considered. Possible implications for that performance are the accumulated precipitation prior to SAR data acquisition, which coincides with the rainy season period. The experimental quad-polarization mode of ALOS/PALSAR- 2 shall be evaluated in the near future over different seasonal conditions to confirm results. Alternatively, further studies are then suggested by focusing on additional features derived from SAR data such as texture and interferometric coherence to increase classification accuracy. These measures would be an interesting data source for monitoring specific land cover classes such as the threatened grasslands and wetlands during periods of frequent cloud coverage. Future investigations could also address multitemporal approaches employing either single or multifrequency SAR.

A bacia hidrográfica do rio Marapanim está localizada na região nordeste do estado do Pará, que se constitui em uma das fronteiras de colonização agrícola mais antiga da Amazônia, e que ao longo do seu processo de ocupação sofreu forte pressão sobre sua cobertura vegetal. O objetivo deste trabalho é analisar a dinâmica do desmatamento, a partir dos usos da terra, e a aplicabilidade das Áreas Prioritárias para Conservação (APC) nas políticas de gestão territorial do estado como o Zoneamento Ecológico Econômico (ZEE). Os resultados mostraram um quadro grave de supressão da cobertura vegetal, que resultou em 80% da área da bacia desmatada. Esse quadro é acompanhado pela fragmentação da floresta o que ocasiona fragmentação de habitats e perda de biodiversidade. Como alternativa para a reversão desse quadro, propõe-se ações associadas ao ordenamento dos planos diretores municipais, à gestão integrada, à formação de cadeia produtiva para uso sustentável dos recursos naturais, à criação de UCs, uma vez que na área da bacia existem apenas duas de uso sustentável que são as Reservas Extrativistas Marinhas Cuiara Cuinarana e Mestre Lucindo, a fim de garantir a conservação e proteção dos remanescentes florestais na região da bacia hidrográfica do rio Marapanim. A B S T R A C TThe Marapanim River Basin, located in the northeastern region of Pará, is one of the oldest agricultural colonization frontiers in the Amazon, which caused strong pressure on the original vegetation during the occupation process. The objective of this work is to analyze the dynamics of deforestation due to land use and the importance of the Priority Areas for Conservation (PAC) for the state's territorial management policies such as the Economic Ecological Zoning (EEZ). The results showed that 80% of the basin area is already deforested. The consequences are forest fragmentation, which leads to fragmentation of habitats and loss of biodiversity. To mitigate the problem, the authors propose associated actions to (i) the municipal management plans, (ii) the integrated management, (iii) the creation of productivity chains for the sustainable use of natural resources, and (iv) the implementation of new conservation units, since there are actually only two units for sustainable use that are Marine Extractive Reserves Cuiara Cuinarana and Mestre Lucindo in the basin area. Such a methodology will ensure conservation and protection of the remaining forests in the Marapanim river basinKey words: Land use. Biodiversity. River basin.

Qualis indexed Engineering Journal and Science Journal to publish paper with DOI, NAAS Rating and journal has global recognized indexing Open Access International Journal

A Faixa de Fronteira da Amazônia Legal é uma região complexa e com grande contraste social, ambiental e econômico. Cáceres (MT) e Oriximiná (PA) ilustram essa realidade: tem origens similares, ligadas à dinâmica dos rios, mas percorreram trajetórias inteiramente diferentes após a intervenção do governo federal na Amazônia, a partir de 1960. Atualmente, Cáceres possui economia com base no comércio, serviços, turismo e, principalmente, na agropecuária extensiva, que corresponde a 82,8% da área desmatada no município. Oriximiná tem na exploração de bauxita a sua base econômica, apresentando 94% de seu território ocupado por floresta nativa; em 2014, a pecuária ocupava 34% da área desmatada no município. O objetivo deste trabalho é analisar como o uso da terra influencia as dinâmicas territoriais desses municípios, e como estes se relacionam com suas fronteiras. Para a realização deste trabalho foram empregados dados de uso e cobertura da terra, referentes aos anos de 2004 e 2014, oriundos do mapeamento realizado pelo Projeto TerraClass (2016), além de informações provenientes de levantamento bibliográfico.

Reports on GRSS society Chapter activities in Brazil.