Search

This manuscript reports the feasibility of a sequential convolutional neural network (CNN) machine-learning model that correctly identifies 11 North American softwood species from 14× magnified macroscopic end-grain images. The convolutional network contained a large kernel size, max pooling layers, and leaky rectified linear units to accelerate training. To reduce overfitting of training data, we employed L2 regularization, custom initialization, and stratified 5-fold cross-validation techniques. The database consisted of 1789 wood end-grain images. The training data set consisted of 1431 images, whereas the validation set had approximately 358 images. In both sets, the input image size was 227 pixels × 227 pixels. Data augmentation was performed on-the-fly by flipping, rotating, and zooming the images. We tested the performance of the CNN against precision, sensitivity, specificity, F1 score, and adjusted accuracy. The adjusted accuracy for the entire model was 94.0%. Confusion matrices indicated the lowest performance was in correctly classifying ponderosa pine (Pinus ponderosa Douglas ex P. Lawson & C. Lawson) and eastern spruce (Picea spp. A. Dietr.) group with an average sensitivity of 89.0% for each. Even though high validation accuracy (>94.0%) was achieved, we concluded that a much larger data set is needed for wood identification to obtain industrially accurate identification of softwoods, mainly due to their visual and macroscopic similarities.

In this study, triangular specimens of southern pine (Pinus spp.; SP) generated by a star-sawn process were characterized according to knots and deformation. SP specimens were used to understand the differences among glue-line combinations of radial-to-radial, radial-to-tangential, and tangential-to-tangential faces bonded with phenol resorcinol formaldehyde resin. The specimens were tested for shear strength, dimensional stability, wood failure, and delamination rate in accordance with ASTM D1037 and D2559 standards. Among the star-sawn triangular samples studied, bows in tangential-face sections occurred the most. The radial-face sections of SP triangular specimens had more knots but a much lesser degree of deformation than the tangential-face sections. The tangential-to-tangential face glue-line samples showed a lower shear strength, more wood failure, and a greater tendency of delamination and dimensional change, especially when subjected to wet conditions. Confocal microscopic pictures revealed that the tangential-to-tangential glue line showed a greater tendency of deformation in the earlywood part and helped to explain the reason for poor glue-line durability and low shear strength. This article revealed that the star-sawn–process generated wood radial-face samples were more stable than others tested and are perhaps a good alternative for massive panel manufacturing.

Roadside right-of-ways (ROWs) undergo regular disturbances such as mowing, maintenance, wrecks, and road developments, which affect soils, groundwater, surface hydrology, and the composition of vegetation. Roadsides can provide and support an environment for diverse plant communities, but management practices have reduced native grasses, wildflowers, and woody plants. Woody plants are not desirable for traffic safety, maintenance, and visibility along road ROWs. Therefore, the objectives of this study were to investigate effects of roadside mowing frequency on native and nonnative herbaceous and woody plant vertical height coverage and native and nonnative woody stem density within plant communities along highway ROWs. We subdivided 10 research plots, systematically situated along Highway 25 in Oktibbeha and Winston counties, Mississippi, to receive 1) four or more mowings annually, 2) one mowing during fall, and 3) one mowing during fall with supplemental native wildflower seeding. We differentiated upland plots on the basis of soil drainage in upward hills. Riparian (lowland) areas were influenced by overbank inundations from streams and drainages, and were typically spanned by bridges or box culverts. We used line transects to sample vegetation. We detected 277 plant species, including native and nonnative forbs, legumes, grasses, rushes, sedges, and woody perennials (vines, shrubs, and trees). Nonnative grasses exhibited the greatest percent coverage (>90%) in all treatments. Woody plants, including vines, trees, and shrubs, comprised 4.65, P ≤ 0.04), seasons (F1,59 > 12.78, P ≤ 0.01), and between years (F1,59 > 4.91, P ≤ 0.03), but did not differ in height categories among treatments. Of the 68%) of the stem counts, whereas 24% were trees and

Although incipient fungal decay of wood may be difficult to detect in early stages, it causes a significant decrease in wood strength. Developing a reliable non-destructive identification method of decay to overcome wood replacement costs is necessary. This study examined mass losses and compression strength decrease of a softwood, spruce pine (Pinus glabra), and a hardwood, quaking aspen (Populus tremuloides), exposed to two brown rot (Gloeophyllum trabeum and Postia placenta) and two white rot (Trametes versicolor and Irpex lacteus) fungi, and identified fungal volatile organic compounds (VOCs) collected over 12 weeks of decay. Principal component analysis (PCA) of VOCs spectra differentiated volatiles emitted from sound wood and wood exposed to fungi. Volatile compounds from two fungal species revealed distinctive patterns of early and late decay stages in each wood species. The overall distinct volatile patterns of fungal decay showed promising results for development of non-destructive identification of incipient decay in wooden building structures.

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.

Activated carbon was prepared from pyrolyzed pinewood char using KOH, H3PO4, H2O2, and heat-only treatments. Activated carbon prepared by the heat-only treatment had a total surface area of 233.2 m2/g, a total pore volume of 0.138 cm3/g, a microporous surface area of 129.9 m2/g, and a microporous volume of 0.07 cm3/g. The most significant improvement of pore properties for the chemically treated pinewood char was obtained by the KOH treatment, which produced a total surface area of 1124.4 m2/g, a total pore volume of 0.723 cm3/g, a microporous surface area of 923.6 m2/g, and a microporous volume of 0.485 cm3/g. After the H3PO4 treatment, pinewood char had a total surface area of 455.5 m2/g, a total pore volume of 0.251 cm3/g, a microporous surface area of 393.3 m2/g, and a microporous volume of 0.211 cm3/g. The least significant improvement was obtained from the H2O2 treatment, which produced a total surface area of 363.0 m2/g, a total pore volume of 0.202 cm3/g, a microporous surface area of 271.5 m2/g, and a microporous volume of 0.141 cm3/g. Transmission electron microscopy (TEM), thermogravimetric analysis (TGA), and Fourier transform infrared spectroscopy (FTIR) were performed to compare separate treatment stabilities and functional group properties.

Native grasses and native wildflowers are declining, especially along roadside right-of-ways because of intensive mowing and herbicide management practices. Roadside right-of-ways undergo regular disturbances such as mowing, maintenance, and road developments that affect soils, groundwater, surface hydrology, and vegetation composition. We investigated species richness and percent coverage within plant communities along highway right-of-ways to determine if reduced mowing increased native plant coverage. The study was conducted using 10 research plots situated along Highway 25 in Oktibbeha and Winston counties, Mississippi. Each research plot consisted of three different treatments as follows: one that included greater than four mowings per year, one mowing only in fall, and one mowing only in fall with a supplemental native wildflower seeding. Using line transect sampling, we detected 277 plant species, which included native and nonnative forbs, legumes, grasses, rushes, sedges, and woody perennials (vines, shrubs, and trees). Total percent coverage of native and nonnative plants within different growth form categories did not differ among treatments (F2,96 = 0.45, P = 0.83). However, coverage differed between uplands and lowlands (F1,96 = 18.22, P ≤ 0.001), between years (F1,96 = 14.54, P ≤ 0.001), between fall and spring seasons (F1,96 = 16.25, P ≤ 0.001), and interacted between years and seasons (F1,96 = 24.08, P ≤ 0.001) and seasons and elevations (F1,96 = 5.00, P ≤ 0.001). Nonnative agronomic grasses exhibited the greatest coverage (> 90%) in all treatments. Percent coverage of each plant growth form was greatest in lowlands. Our research showed an increase of native grasses and wildflower species along roadsides with a reduced mowing regimen. We concluded that the timing and intensity of mowing for the duration of our study had little effect on the species composition of plant communities. However, one mowing per year retained agronomic plant coverage for erosion control and soil stabilization during roadside maintenance. Specific proactive management implementations can include native plantings, selective herbicide use to decrease nonnative grasses, continual mowing from roadside edge to 10 m, and only one mowing in late fall, but with an extension of the boundary to reach beyond 10 m from the roadside edge to suppress the invasion of woody plants, which could lead to lower long-term maintenance costs.