The application of artificial intelligence (AI) techniques has improved the accuracy of forest species identification, particularly in timber inventories conducted under Sustainable Forest Management (SFM). This study developed and evaluated machine learning models to recognize 16 Amazonian timber species using digital images of tree bark. Data were collected from three SFM units located in Nova Maringá, Feliz Natal, and Cotriguaçu, in the state of Mato Grosso, Brazil. High-resolution images were processed into sub-images (256 × 256 pixels), and two feature extraction methods were tested: Local Binary Patterns (LBP) and pre-trained Convolutional Neural Networks (ResNet50, VGG16, InceptionV3, MobileNetV2). Four classifiers—Support Vector Machine (SVM), Artificial Neural Networks (ANN), Random Forest (RF), and Linear Discriminant Analysis (LDA)—were used. The best result (95% accuracy) was achieved using ResNet50 with SVM, confirming the effectiveness of transfer learning for species recognition based on bark texture. These findings highlight the potential of AI-based tools to enhance accuracy in forest inventories and support decision-making in tropical forest management.

The Brazil nut tree is considered symbolic of the Brazilian Amazon in function of its great importance, being one of the most significant extractivist products and a subsistence practice of the Indigenous people in many municipalities in Pará state. One of the main problems in different communities is related to the marketing process since it is not possible to distinguish the origin of the nuts and this causes inconvenience. The study evaluated the potential of VIS/NIR spectroscopy to identify the origin of leaves and nuts from Brazil nut trees growing in two indigenous villages, in the Xipaya Indigenous Lands, Pará state. Analysis was performed based on CIEL*a*b* parameters and using VIS (360–740 nm) and near-infrared spectra (1000–2500 nm). The samples were differentiated according to means tests, principal component analysis (PCA), and classification analysis based on k-NN. Color parameters and spectra were similar in both communities. Classification models based on k-NN produced adequate results for the distinction of villages in all evaluated situations, with accuracy of 98.54% for leaves, 89% and 90.91% for nuts with and without shell, respectively. Near infrared can be applied in forests as a technique for previous provenance identification and contribute to the subsistence and sustainable practice of extraction.

Gap size is one of the main variables used to quantify the environmental consequences of forest management that can help in quantifying and monitoring changes in clearing areas. This study aimed to characterize gaps from harvested individuals, quantify the resulting forest damage, and adjust equations to describe gaps after tree cutting. Our research was conducted in three phytophysiognomies of the eastern Pará Amazon. We performed descriptive analyses using data on gap size and damage to the remaining individuals in each phytophysiognomy. We then applied predictive modeling to estimate clearing size using a generalized linear model. Modeling parameters included Gaussian, gamma, and inverse Gaussian families, with linking and transforming functions of the analyzed variables. Among the three phytophysiognomies, the largest clearings were observed in open ombrophilous forests with lianas (27,650 to 548,460 m²), with 56 large gaps, 148 medium, and 113 small. The model with three linear predictors (diameter, height, and phytophysiognomy), inverse Gaussian distribution, and logarithmic link function showed the best fit. There were notable differences in clearing size across phytophysiognomies, suggesting that the phytophysiognomy should be considered when planning measures to mitigate the impacts of forest management.

The growth and production of a forest stand depend on indicators such as the site's productive capacity, which can be defined as the site's potential to produce wood, or another product in each location, for a given species or clone. This study compared traditional methods and artificial neural networks in the classification of the productive capacity of sites in Eucalyptus urograndis plantations located in the Jari region, western Pará state. For this, 593 permanent circular plots of 500 m² each were randomized, where 38,072 trees were monitored annually from 2013 to 2017. In each plot, the diameter at the height of 1.30 from the ground (DBH, in cm) and the total height (Ht, in meters) of nine trees were measured. Three traditional methods were evaluated: guide-curve method (GC), difference equation method (DE), and parameter prediction method (PP). The statistical criteria used to assess the quality of the classification were: BIAS (%), mean squared error (RMSE (%)), and Pearson correlation coefficient (r). Artificial neural networks were superior to traditional methods, indicating the potential of the algorithm to model the productive capacity of a site for forest stands.

The application of artificial intelligence (AI) techniques has improved the accuracy of forest species identification, particularly in timber inventories conducted under Sustainable Forest Management (SFM). This study developed and evaluated machine learning models to recognize 16 Amazonian timber species using digital images of tree bark. Data were collected from three SFM units located in Nova Maringá, Feliz Natal, and Cotriguaçu, in the state of Mato Grosso, Brazil. High-resolution images were processed into sub-images (256 × 256 pixels), and two feature extraction methods were tested: Local Binary Patterns (LBP) and pre-trained Convolutional Neural Networks (ResNet50, VGG16, InceptionV3, MobileNetV2). Four classifiers—Support Vector Machine (SVM), Artificial Neural Networks (ANN), Random Forest (RF), and Linear Discriminant Analysis (LDA)—were used. The best result (95% accuracy) was achieved using ResNet50 with SVM, confirming the effectiveness of transfer learning for species recognition based on bark texture. These findings highlight the potential of AI-based tools to enhance accuracy in forest inventories and support decision-making in tropical forest management.

Accurate estimation of timber volume is crucial for successful forest management. In tropical forests, high species diversity and the variability of tree biometric attributes increase the difficult...