The tropical forest is characterized by expressive biomass and stores high amounts of carbon, which is an important variable for climate monitoring. Thus, studies aiming to analyze suitable methods to predict biomass are crucial, especially in the tropics, where dense vegetation makes modeling difficult. Thus, the objective of the present study was to estimate aboveground biomass (AGB) in a tropical forest area with selective logging in the Amazon forest using the Random Forest (RF) machine learning algorithm and LiDAR data. For this, 85 sample units were used at Fazenda Cauaxi, in the municipality of Paragominas, Pará State. LiDAR data were collected in 2014 and made available by the Sustainable Landscapes Project. The software R was used for data analysis. Among the LiDAR metrics, the average height was used as it had the greatest significance to compose the model. The model presented a pseudo R² of 0.69 (value obtained by the RF), Spearman's Correlation Coefficient of 0.80, RMSE of 47.05 Mg.ha-1 (19.84%), and Bias of 2.06 Mg.ha-1 (0.87%). With the results, it was possible to infer that the average height metric was enough to estimate AGB in a tropical forest with selective logging, in addition, the RF algorithm the biomass to be estimated, which can be used to assist in monitoring and action management in areas of selective logging and serve as a basis for climate change mitigation policies.

The objective of this study was to correlate the biophysical parameters of forage cactus with visible vegetation indices obtained by unmanned aerial vehicles (UAVs) and predict them with machine learning in different agricultural systems. Four experimental units were conducted. Units I and II had different plant spacings (0.10, 0.20, 0.30, 0.40, and 0.50 m) with East–West and North–South planting directions, respectively. Unit III had row spacings (1.00, 1.25, 1.50, and 1.75 m), and IV had cutting frequencies (6, 9, 12 + 6, and 18 months) with the clones “Orelha de Elefante Mexicana”, “Miúda”, and “IPA Sertânia”. Plant height and width, cladode area index, fresh and dry matter yield (FM and DM), dry matter content, and fifteen vegetation indices of the visible range were analyzed. The RGBVI and ExGR indices stood out for presenting greater correlations with FM and DM. The prediction analysis using the Random Forest algorithm, highlighting DM, which presented a mean absolute error of 1.39, 0.99, and 1.72 Mg ha⁻¹ in experimental units I and II, III, and IV, respectively. The results showed potential in the application of machine learning with RGB images for predictive analysis of the biophysical parameters of forage cactus.

The objective of this work was to evaluate the use of Landsat 8/OLI images to differentiate the age and estimate the total volume of Pinus elliottii, in order to determine the applicability of these data in the planning and management of forest activity. Fifty-three sampling units were installed, and dendrometric variables of 9-and-10-year-old P. elliottii commercial stands were measured. The digital numbers of the image were converted into surface reflectance and, subsequently, vegetation indices were determined. Red and near-infrared reflectance values were used to differentiate the ages of the stands. Regression analysis of the spectral variables was used to estimate the total volume. Increase in age caused an addition in reflectance in the near-infrared band and a decrease in the red band. The general equation for estimating the total volume for P.elliottii had an R2adj of 0.67 with a Syx of 31.46 m3 ha-1. Therefore, the spectral data with medium spatial resolution from the Landsat 8/OLI satellite can be used to distinguish the growth stages of the stands and can, thus, be used in the planning and proper management of forest activity on a spatial and temporal scale.

This study aimed to assess the potential of machine learning models applied to high spatial resolution images from UAVs for estimating the aboveground biomass (AGB) of forage grass cultivated in the Brazilian semiarid region. The fresh and dry AGB were determined in Cenchrus ciliare plots with an area of 0.04 m². Spectral data were obtained using a multispectral sensor (Red, Green, and NIR) mounted on a UAV, from which 45 vegetation indices were derived, in addition to a structural variable representing plant height (H95). Among these, H95, GDVI, GSAVI2, GSAVI, GOSAVI, GRDVI, and CTVI exhibited the strongest correlations with biomass. Following multicollinearity analysis, eight variables (R, G, NIR, H95, CVI, MCARI, RGR, and Norm G) were selected to train Random Forest (RF), Support Vector Machine (SVM), and XGBoost models. RF and XGBoost yielded the highest predictive performance, both achieving an R² of 0.80 for AGB—Fresh. Their superiority was maintained for AGB—Dry estimation, with R² values of 0.69 for XGBoost and 0.67 for RF. Although SVM produced higher estimation errors, it showed a satisfactory ability to capture variability, including extreme values. In modeling, the incorporation of plant height, combined with spectral data obtained from high spatial resolution imagery, makes AGB estimation models more reliable. The findings highlight the feasibility of integrating UAV-based remote sensing and machine learning algorithms for non-destructive biomass estimation in forage systems, with promising applications in pasture monitoring and agricultural land management in semi-arid environments.

O objetivo deste trabalho foi realizar o mapeamento das áreas suscetíveis a ocorrência de incêndios na Estação Ecológica do Taim, Rio Grande do Sul. Para a obtenção das variáveis estáticas e dinâmicas, foram utilizadas imagens do satélite Landsat 8 e imagens de Radar para a determinação da topografia da área de estudo. Como variáveis dinâmicas utilizou-se a precipitação, temperatura e uso e cobertura da terra, enquanto que variáveis estáticas foram a hipsometria, declividade e distância das estradas. Cada variável foi estratificada e posteriormente ponderada numericamente quanto a sua suscetibilidade a ocorrência a incêndio. As variáveis dinâmicas e estáticas geradas foram integradas utilizando uma equação ponderada resultando no risco de incêndios para a área de estudo. A região central da Estação Ecológica do Taim apresentou maior suscetibilidade a incêndios, englobando a classe de alto risco, totalizando 4.219,56 ha (41,61%), enquanto as regiões periféricas apresentaram risco muito baixo a ocorrência de incêndios, abrangendo 5.419,35 ha (53,44%). As variáveis de maior contribuição à ocorrência de incêndios corresponderam ao uso e cobertura da terra e a temperatura, sendo as áreas de maior risco localizadas na parte central e próximo às estradas, nas quais estão ocupadas por campo nativo. Assim, esses locais devem ter maior atenção e recursos para combate de possíveis incêndios. Palavras-chave: Landsat 8; variáveis dinâmicas e estáticas; geoprocessamento. FIRE RISK AT THE ECOLOGIAL STATION OF TAIM, RIO GRANDE DO SUL ABSTRACT: The objective of this work was to map the areas susceptible to the occurrence of fires at the Taim Ecological Station, Rio Grande do Sul. In order to obtain the static and dynamic variables, Landsat 8 satellite images and Radar images were used to determine the topography of the study area. As dynamic variables were used the precipitation, temperature and land use and coverage, while static variables were hypsometry, slope and distance of roads. Each variable was stratified and numerically weighted as to its susceptibility to fire occurrence. The dynamic and static variables generated were integrated using a weighted equation resulting in fire risk for the study area. The central region of the Taim Ecological Station presented higher susceptibility to fires, encompassing the high risk class, totaling 4,219.56 ha (41.61%), while the peripheral regions had a very low risk of occurrence of fires, covering 5,419.35 ha (53.44%). The variables of greatest contribution to the occurrence of fires corresponded to the land use and land cover and the temperature, being the areas of greater risk in the central region and near the roads, in which they are occupied by the native field. Thus, these sites should have greater attention and resources to combat possible fires. Keywords: Landsat 8; dynamic and static variables; geoprocessing.

USO DE IMAGENS DE MÉDIA RESOLUÇÃO ESPACIAL PARA O MONITORAMENTO DE DOSSÉIS DE Eucalyptus grandis