This study aimed to investigate and compare the qualitative and quantitative anatomical characteristics of Acacia mangium and Acacia hybrid in plantation forests in Vietnam. The qualitative and quantitative anatomical characteristics were evaluated according to the International Association of Wood Anatomists list of microscopic features for hardwood identification. In terms of qualitative features, A. mangium had a rough, hard, and fissured bark surface with a golden brown to dark brown color, whereas A. hybrid had a smooth and slightly scaly bark surface with greenish brown to greyish brown color, and yellowish white to pale white spots. Moreover, the heartwood–sapwood color and microscopic features of both species were identical. In terms of quantitative features, A. mangium had higher values in the tangential diameter of vessel lumina, vessel per square millimeter, ray number per millimeter, fiber length, and fiber wall thickness than A. hybrid, whereas A. hybrid had a higher ray height and lumen diameter than A. mangium. Thus, it is suggested that bark morphology and some quantitative anatomical characteristics can be used for identification and evaluation of wood quality between A. mangium and A. hybrid growing in Vietnam.

This study investigated the anatomical and non-anatomical characteristics of six wood species, Acacia mangium, Acacia hybrid, Dillenia pentagyna, Anacardium occidentale, Hevea brasiliensis, and Melaleuca cajuputi, from a plantation in Vietnam. The anatomical characteristics and non-anatomical characteristics were observed following the International Association of Wood Anatomists (IAWA) list. All species showed diffuse porosity and non-septate fibers. Exclusively solitary vessels were only observed in M. cajuputi. Vestured pits were observed in A. mangium, A. hybrid, and M. cajuputi, and tyloses were found in A. occidentale and H. brasiliensis. We observed vasicentric axial parenchyma in A. mangium, A. hybrid, A. occidentale, and H. brasiliensis, whereas diffuse axial parenchyma was observed in D. pentagyna and M. cajuputi. Further, prismatic crystals in the axial parenchyma cells existed in A. mangium, A. hybrid, and H. brasiliensis, and raphides in ray cells were observed in D. pentagyna. Silica bodies in ray cells were found in A. occidentale and M. cajuputi. H. brasiliensis exhibited the greatest vessel diameter and ray height, with D. pentagyna exhibiting the greatest fiber length and wall thickness. All the species showed considerable differences in heartwood fluorescence, water and ethanol extract colors, and froth test reactions.

Based on the sclereids in the bark of oak species, a convolutional neural network (CNN) was employed to validate species classification performance and its influencing factors. Three optimizers including stochastic gradient descent (SGD), adaptive moment estimation (Adam), root mean square propagation (RMSProp), and dataset augmentation were adopted. The accuracy and loss stabilized at approximately 15 to 20 and 70 to 80 epochs for the augmented and non-augmented condition, respectively. In the last five epochs, the RMSProp-augmented condition achieved the highest accuracy of 89.8%, whereas the Adam-augmented condition achieved the lowest accuracy of 73.8%. Regarding the loss, SGD-non-augmented condition was the lowest at 0.498, whereas Adam-augmented condition was the highest at 2.740. The highest accuracy was influenced by RMSProp at 0.194. Dataset augmentation had a significant influence on accuracy at 0.456. Homogeneous subsets among the validation conditions indicated that the accuracy and loss were classified into the same subset using an augmented dataset during the training, regardless of the optimizer. Only Adam and RMSProp with non-augmented datasets were categorized into the same subset during the test. Hence, species classification using CNN and sclereid characteristics in the bark was feasible, and RMSProp with augmented datasets showed optimal performance for species classification.

The macroscopic and microscopic anatomical characteristics of wood impact its utilization. This study investigated and compared the anatomical characteristics of six Korean oak wood species: Quercus variabilis, Quercus serrata, Quercus mongolica, Quercus dentata, Quercus aliena, and Quercus acutissima. Microscopic anatomical characteristics were evaluated according to the International Association of Wood Anatomists’ list for hardwood identification. Q. variabilis had a corky bark texture, with a color similar to that of Q. serrata. Flat ridges and shallow-fissured barks were observed in Q. serrata and Q. mongolica. The heartwood color was darker than that of sapwood in all species, with color variations. Q. variabilis had heartwood–sapwood colors similar to those of Q. acutissima, while Q. mongolica and Q. aliena presented similar heartwood–sapwood colors. Concerning microscopic features, Q. variabilis and Q. acutissima exhibited similar latewood vessel arrangements, featuring diagonal and/or radial patterns. In contrast, dendritic-to-diagonal patterns of vessels with angular outlines were observed in Q. serrata, Q. mongolica, Q. dentata, and Q. aliena. Additionally, Q. variabilis and Q. acutissima had vasicentric, confluent, and unilateral paratracheal axial parenchyma in the latewood. In summary, bark morphology, bark color, wood color, and latewood vessel characteristics can be used as identification keys for Korean oak species.

The objective of this study was to examine and compare radial variation of the anatomical characteristics and the transition age from juvenile to mature wood of the six Korean oak wood species: Quercus variabilis (Qv), Quercus serrata (Qs), Quercus mongolica (Qm), Quercus dentata (Qd), Quercus aliena (Qal), and Quercus acutissima (Qac). Quantitative anatomical features were observed from the pith to the bark at five growth-ring intervals using optical microscopy. A segmented regression model was used to evaluate the transition from juvenile wood to mature wood. The clearest transition from juvenile to mature wood was observed in the radial variation of the earlywood vessel diameter and fiber length. The maturation age of the six Korean oak species ranged from 19 to 44 years. Qv exhibited the highest values for latewood vessel diameter, fiber length, and fiber diameter. Qac displayed the highest values for earlywood vessel diameter and fiber wall thickness. The highest fiber lumen diameter was observed for Qm. The differences in earlywood and latewood vessel diameters and fiber lengths could be utilized as identification keys for these species. Earlywood vessel diameter and fiber length have emerged as the most reliable indicators for estimating the transition from juvenile to mature wood.

This study aims to verify the wood classification performance of convolutional neural networks (CNNs), such as VGG16, ResNet50, GoogLeNet, and basic CNN architectures, and to investigate the factors affecting classification performance. A dataset from 10 softwood species consisted of 200 cross-sectional micrographs each from the total part, earlywood, and latewood of each species. We used 80% and 20% of each dataset for training and testing, respectively. To improve the performance of the architectures, the dataset was augmented, and the differences in classification performance before and after augmentation were compared. The four architectures showed a high classification accuracy of over 90% between species, and the accuracy increased with increasing epochs. However, the starting points of the accuracy, loss, and training speed increments differed according to the architecture. The latewood dataset showed the highest accuracy. The epochs and augmented datasets also positively affected accuracy, whereas the total part and non-augmented datasets had a negative effect on accuracy. Additionally, the augmented dataset tended to derive stable results and reached a convergence point earlier. In the present study, an augmented latewood dataset was the most important factor affecting classification performance and should be used for training CNNs.