This technical note determines the feasibility of using an InceptionV4_ResNetV2 convolutional neural network (CNN) to correctly identify hardwood species from macroscopic images. The method is composed of a commodity smartphone fitted with a 14× macro lens for photography. The end-grains of ten different North American hardwood species were photographed to create a dataset of 1869 images. The stratified 5-fold cross-validation machine-learning method was used, in which the number of testing samples varied from 341 to 342. Data augmentation was performed on-the-fly for each training set by rotating, zooming, and flipping images. It was found that the CNN could correctly identify hardwood species based on macroscopic images of its end-grain with an adjusted accuracy of 92.60%. With the current growing of machine-learning field, this model can then be readily deployed in a mobile application for field wood identification.

This study reports the feasibility of using deep convolutional neural networks (CNN), for automatically detecting knots on the surface of wood with high speed and accuracy. A limited dataset of 921 images were photographed in different contexts and divided into 80:20 ratio for training and validation, respectively. The “You only look once” (YoloV3) CNN-based architecture was adopted for training the neural network. The Adam gradient descent optimizer algorithm was used to iteratively minimize the generalized intersection-over-union loss function. Knots on the surface of wood were manually annotated. Images and annotations were analyzed by a stack of convolutional and fully connected layers with skipped connections. After training, model checkpoint was created and inferences on the validation set were made. The quality of results was assessed by several metrics: precision, recall, F1-score, average precision, and precision x recall curve. Results indicated that YoloV3 provided knot detection time of approximately 0.0102 s per knot with a relatively low false positive and false negative ratios. Precision, recall, f1-score metrics reached 0.77, 0.79, and 0.78, respectively. The average precision was 80%. With an adequate number of images, it is possible to improve this tool for use within sawmills in the forms of both workstation and mobile device applications.

This manuscript confirms the feasibility of using a long short-term memory (LSTM) recurrent neural network (RNN) to forecast lumber stock prices during the great and Coronavirus disease 2019 (COVID-19) pandemic recessions in the USA. The database was composed of 5012 data entries divided into recession periods. We applied a timeseries cross-validation that divided the dataset into an 80:20 training/validation ratio. The network contained five LSTM layers with 50 units each followed by a dense output layer. We evaluated the performance of the network via mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE) for 30, 60, and 120 timesteps and the recession periods. The metrics results indicated that the network was able to capture the trend for both recession periods with a remarkably low degree of error. Timeseries forecasting may help the forest and forest product industries to manage their inventory, transportation costs, and response readiness to critical economic events.

Heat treatment (HT) of a mixture of tannins and inorganic boron compounds showed effective results against wood decay organisms. Boron compounds play a critical role in the preservation of wood against wood decay organisms. The use of tannins and HT represents a relatively new environmentally friendly approach to the wood preservation industry. The aim of this study was to investigate the effect of tannin impregnation and HT on boron depletion, and termite and fungi resistance. Southern yellow pine (SYP) and yellow-poplar (YP) cube samples were used for this study. A mixture of condensed tannins from the Quebracho tree and disodium octaborate tetrahydrate (DOT) was injected into the specimens using a vacuum/pressure cycle, and the specimens were then heat-treated under N₂ atmosphere for four hours at 190 °C to investigate both the tannin’s fixative ability to reduce boron leaching and the performance of the mixture against brown and white-rot fungi and termites. Tannins restricted boron leaching in 46% and 34% for SYP and YP, respectively, and also significantly increased the resistance against white-rot fungi for YP. Tannins and HT showed unpredictably good performance against termites. Tannins may be acting to denature proteins; in that case, fungal enzymes would be inhibited. This study revealed the importance of HT on a mixture of boron and tannins to decrease boron leaching and increase the durability of preservative systems.

Cross-laminated timber (CLT) market demand is on the rise in the United States. Adequate protective measures have not been extensively studied. The objective of this study was to investigate the weathering performance of exterior wood coatings. We evaluated coated CLT sample surfaces based on visual appearance, color change (CIE*L*a*b), gloss changes, and water intrusion. From the five exterior wood coatings evaluated, only two showed adequate performance after twelve months field exposure. Based on visual ratings following the ASTM procedures, coating failure occurs more quickly in Mississippi than in Wisconsin, due to its greater decay zone. Both location and coating type impacted the aging of the samples. Artificial weathering results were consistent with natural weathering indicating the two adequate coatings were the most resistant to failure, color, and gloss change. For future studies, new coatings designed for the protection of end-grain in CLT panels should be a target of research and development.

Microscopic wood identification plays a critical role in many economically important areas in wood science. Historically, producing and curating relevant and representative microscopic cross-section images of wood species is limited to highly experienced and trained anatomists. This manuscript demonstrates the feasibility of generating synthetic microscopic cross-sections of hardwood species. We leveraged a publicly available dataset of 119 hardwood species to train a style-based generative adversarial network (GAN). The proposed GAN generated anatomically accurate cross-section images with remarkable fidelity to actual data. Quantitative metrics corroborated the capacity of the generative model in capturing complex wood structure by resulting in a Fréchet inception distance score of 17.38. Image diversity was calculated using the Structural Similarity Index Measure (SSIM). The SSIM results confirmed that the GAN approach can successfully synthesize diverse images. To confirm the usefulness and realism of the GAN generated images, eight professional wood anatomists in two experience levels participated in a visual Turing test and correctly identified fake and actual images at rates of 48.3 and 43.7%, respectively, with no statistical difference when compared to random guess. The generative model can synthesize realistic, diverse, and meaningful high-resolution microscope cross-section images that are virtually indistinguishable from real images. Furthermore, the framework presented may be suitable for improving current deep learning models, helping understand potential breeding between species, and may be used as an educational tool.