Considerando a crescente demanda por mudas florestais e a escassez de matérias-primas dos substratos utilizados para o crescimento das plantas, faz-se necessário avaliar novos componentes e formulações que assegurem a qualidade das mudas. Nesse experimento foram estudados o desenvolvimento e a qualidade de mudas clonais de Eucalyptus urophylla x E. grandis, provenientes de miniestacas, em função de nove composições de substrato produzidos a partir de vermiculita granulometria fina, casca de arroz carbonizada e fibra de coco em tubetes de 50 mL. Foram avaliados as propriedades físicas dos substratos, o desenvolvimento morfológico e a qualidade do sistema radicular das mudas, aos 90 dias após o estaqueamento. Os substratos com maior porosidade total promovem maior qualidade do sistema radicular o que, consequentemente, resulta em mudas com maior diâmetro, massa seca aérea e radicular e Índice de Qualidade de Dickson. Outros valores para as características físicas dos substratos, diferentes dos citados na literatura, também podem ser considerados adequados.

The correct capture of forest operations information carried out in forest plantations can help in the management of mechanized harvesting timber. Proper management must be able to dimension resources and tools necessary for the fulfillment of operations and helping in strategic, tactical, and operational planning. In order to facilitate the decision making of forest managers, this work aimed to analyze the performance of machine learning algorithms in estimating the productivity of timber harvesters. As predictors of productivity, we used the availability of hours of machine use, individual mean volumes of trees, and terrain slopes. The dataset was composed of 144,973 records, carried out over a period of 28 months. We tested the predictive performance of 24 machine learning algorithms in default mode. In addition, we tested the performance of blending and stacking joint learning methods. We evaluated the model’s fit using the root mean squared error, mean absolute error, mean absolute percentage error, and determination coefficient. After cleaning the initial database, we used only 1.12% to build the model. Learning by blending ensemble stood out with a determination coefficient of 0.71 and a mean absolute percentage error of 15%. From the use of data from machine learning algorithms, it became possible to predict the productivity of timber harvesters. Testing a variety of machine learning algorithms with different dynamics contributed to the machine learning technique that helped us reach our goal: maximizing the model’s performance by conducting experimentation.

Http://dx.doi.org/10.5902/198050985082Os componentes utilizados na produção de substratos influem diretamente no ciclo vegetativo, na qualidade e consequentemente nos custos de produção das mudas. Nesse experimento estudou-se o desenvolvimento, qualidade e custos de produção de mudas de Eucalyptus grandis Hill ex Maiden × Eucalyptus urophylla S. T. Blake, por meio de propagação sexuada, utilizando 12 composições de substrato. A análise dos resultados evidenciou que os substratos puros, a exceção da fibra de coco, não apresentaram características físicas adequadas para a produção de mudas, via sexuada, de Eucalyptus grandis Hill ex Maiden × Eucalyptus urophylla S. T. Blake em tubetes. Os melhores resultados foram obtidos nos substratos com mistura 1:1 de casca de arroz carbonizada e fibra de coco e na mistura 1:1 de vermiculita e fibra de coco, devido às melhores características morfológicas apresentadas e da possibilidade de redução do tempo de produção, levando à redução no custo final das mudas.

The Brazilian Amazon is recognized worldwide for its biodiversity and it plays a key role in maintaining the regional and global climate balance. However, it has recently been greatly impacted by changes in land use, such as replacing native forests with agricultural activities. These changes have resulted in serious environmental consequences, including significant alterations to climate and hydrological cycles. This study aims to analyze changes in land use and land covered in the Brazilian Amazon between 2001 and 2023, as well as the resulting effects on precipitation variability, land surface temperature, and evapotranspiration. Data obtained via remote sensing and processed on the Google Earth Engine platform were used, including MODIS, CHIRPS, Hansen products. The results revealed significant changes: forest formation decreased by 8.55%, while agricultural land increased by 575%. Between 2016 and 2023, accumulated deforestation reached 242,689 km². Precipitation decreased, reaching minimums of 772.7 mm in 2015 and 726.4 mm in 2020. Evapotranspiration was concentrated between 941 and 1360 mm in 2020, and surface temperatures ranged between 30 °C and 34 °C in 2015, 2020, and 2023. We conclude that anthropogenic transformations in the Brazilian Amazon directly impact vegetation cover and the regional climate. Therefore, conservation and monitoring measures are essential for mitigating these effects.

Diagnosing climate variability and environmental change in floodable regions is essential for understanding and mitigating impacts on natural ecosystems. Our objective was to characterize environmental degradation in the Brazilian Pantanal by identifying changes in vegetation and water cover over a 30-year period using remote sensing techniques. We evaluated surface physical–hydric parameters, including Land Use and Land Cover (LULC) maps, Normalized Difference Vegetation Index (NDVI), Modified Normalized Difference Water Index (MNDWI), Normalized Difference Moisture Index (NDMI), and precipitation data. There was a decrease in the area of water bodies (−9.9%), wetlands (−5.7%), and forest formation (−3.0%), accompanied by an increase in the area of pastureland (7.4%). The NDVI showed significant changes in vegetation cover (−0.69 to 0.81), while the MNDWI showed a decrease in water surface areas (−0.73 to 0.93) and the NDMI showed a continuous decrease in vegetation moisture (−0.53 to 1). Precipitation also decreased over the years, reaching a minimum of 595 mm. Vegetation indices and land use maps revealed significant changes in vegetation and loss of water bodies in the Pantanal, reinforcing the need for sustainable management, recovery of degraded areas, and promotion of ecotourism to balance environmental conservation and local development.