Summary Environmental adaptation and cell differentiation processes are factors that influence the anatomical elements of wood. The objective of this study was to investigate the effect of water deficit on lignin composition in anatomical elements and on the characteristics of vessel-neighboring cells. Six-year-old clones of Eucalyptus urophylla and Eucalyptus grandis × Eucalyptus camaldulensis from wet and dry regions were used. All regions received a rainfall exclusion treatment. Cell wall width, cell wall thickness, and form factor of fibers close to and far from vessels were measured. In the same cells, lignin was measured in the middle lamella and vessels by a fluorescence technique. The vessel differentiation process affected cell wall thickness and lignin composition in neighboring cells. Lignin composition was increased in vessels compared to fibers or vasicentric tracheids. Middle lamella lignin was not affected by vessel differentiation or water deficit in either eucalyptus clone. E. grandis × E. camaldulensis is originally from a dry climate region and, therefore, did not suffer alterations in lignin when subjected to water stress conditions; however, this clone exhibited a higher number of vasicentric tracheids. E. urophylla is originally from a humid climate region and, when subjected to water deficit, showed increased wood lignin composition, which seems to be a strategy for better use of water resources. Alterations in lignin composition of vessel, vasicentric tracheid, and fiber cell walls resulting from exposure to water deficit conditions vary according to eucalyptus species.

No abstract

Background: Multiple challenges are faced by industry and certification agencies when commercializing tropical species. Anatomical similarities of tropical hardwoods impair identification. Deep learning models can facilitate microscopic identification of wood by using sophisticated techniques such as deep convolutional networks (DCNN). Our objective was to microscopically identify 23 commercially available Brazilian wood species using a custom DCNN model. Results:Photographs from microscopic slides of each wood species were processed, and the final data set contained 2,448 images. We applied stratified k-fold cross-validation technique during training to increase model's robustness and trustworthiness. Thus, the dataset was divided into approximately 80% training (1,958 images) and 20% validation (490 images) for each fold. A series of augmentations were performed only on training data to include variations in rotation, zoom, and perspective. Image augmentation was performed on-the-fly. The network consisted of convolutions, max pooling, global average pooling, and fully connected layers. We tested the performance of the DCNN against accuracy, precision, recall, and F1-score on the validation set for each fold. Conclusion:The custom machine learned model accuracy was higher than 0.90. The model's worst performance was identified in distinguishing between Toona ciliata and Khaya ivorensis, which was due more to wood variability than to a machine learning deficiency. Future studies should focus on integration, verification/monitoring, and updating of current models for end user manipulation, trust, ethics, and security.

No abstract