An official website of the United States government
Accurate tree species identification through bark characteristics is essential for effective forest management, but traditionally requires extensive expertise. This study leverages artificial intelligence (AI), specifically the EfficientNet-B3 convolutional neural network, to enhance AI-based tree bark identification, focusing on northern red oak (Quercus rubra), hackberry (Celtis occidentalis), and bitternut hickory (Carya cordiformis) using the CentralBark dataset. We investigated three environmental variables—time of day (lighting conditions), bark moisture content (wet or dry), and cardinal direction of observation—to identify sources of classification inaccuracies. Results revealed that bark moisture significantly reduced accuracy by 8.19% in wet conditions (89.32% dry vs. 81.13% wet). In comparison, the time of day had a significant impact on hackberry (95.56% evening) and northern red oak (80.80% afternoon), with notable chi-squared associations (p < 0.05). Cardinal direction had minimal effect (4.72% variation). Bitternut hickory detection consistently underperformed (26.76%), highlighting morphological challenges. These findings underscore the need for targeted dataset augmentation with wet and afternoon images, alongside preprocessing techniques like illumination normalization, to improve model robustness. Enhanced AI tools will streamline forest inventories, support biodiversity monitoring, and bolster conservation in dynamic forest ecosystems.
more »
« less
Modeling and Monitoring of Wood Moisture Content Using Time-Domain Reflectometry
Time-domain reflectometry (TDR) can monitor the moisture content (MC) of water saturated logs stored in wet-decks where the MC exceeds the range that can be measured using traditional moisture meters (>50%). For this application to become routine, it is required that TDR monitoring of wet-decks occurs after establishment, and tools are needed that automate data collection and analysis. We developed models that predict wood MC using three-rod epoxy encased TDR probes inserted into the transverse surface of bolts (prior wet-deck studies were installed on the tangential surface). Models were developed for southern pine, sweetgum, yellow poplar, hickory, red oak, and white oak using a Campbell Scientific TDR100. For each species, at least 37 bolts were soaked for a minimum of three months and then air dried with TDR waveforms, and MC was periodically recorded. Calibrations were developed between MC and the TDR signal using nonlinear mixed effects models. Fixed effects ranged from excellent (southern pine R2 = 0.93) to poor (red oak R2 = 0.36, hickory R2 = 0.38). Independent of wood species, random effects all had a R2 greater than 0.80, which indicates that TDR detects changes in MC at the individual sample level. Use of TDR combined with a datalogger was demonstrated in an operational wet-deck that monitored changes in MC over 12 months, and in a laboratory trial where bolts were exposed to successive wet-dry cycles over 400 days. Both applications demonstrated the utility of TDR to monitor changes in wood MC in high MC environments where periodic measurement is not feasible due to operational safety concerns. Because a saturated TDR reading indicates a saturated MC, and because of the relatively accurate random effects found here, developing individual species models is not necessary for monitoring purposes. Therefore, application of TDR monitoring can be broadly applied for wet-decks, regardless of the species stored.
more »
« less
- Award ID(s):
- 1916720
- PAR ID:
- 10260009
- Date Published:
- Journal Name:
- Forests
- Volume:
- 11
- Issue:
- 4
- ISSN:
- 1999-4907
- Page Range / eLocation ID:
- 479
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Summary Wood formation determines major long‐term carbon (C) accumulation in trees and therefore provides a crucial ecosystem service in mitigating climate change. Nevertheless, we lack understanding of how species with contrasting wood anatomical types differ with respect to phenology and environmental controls on wood formation.In this study, we investigated the seasonality and rates of radial growth and their relationships with climatic factors, and the seasonal variations of stem nonstructural carbohydrates (NSC) in three species with contrasting wood anatomical types (red oak: ring‐porous; red maple: diffuse‐porous; white pine: coniferous) in a temperate mixed forest during 2017–2019.We found that the high ring width variability observed in both red oak and red maple was caused more by changes in growth duration than growth rate. Seasonal radial growth patterns did not vary following transient environmental factors for all three species. Both angiosperm species showed higher concentrations and lower inter‐annual fluctuations of NSC than the coniferous species.Inter‐annual variability of ring width varied by species with contrasting wood anatomical types. Due to the high dependence of annual ring width on growth duration, our study highlights the critical importance of xylem formation phenology for understanding and modelling the dynamics of wood formation.more » « less
-
null (Ed.)Attributes of deadwood in forests, including quantity, landscape position, and state of decay, influence numerous ecosystem processes such as wildfire behavior, tree regeneration, and nutrient cycling. Attributes of deadwood that vary over subdiurnal time steps, including moisture, have not been routinely measured despite the profound effects they have on ecosystem processes. To improve our understanding of forest deadwood subdiurnal moisture dynamics, we installed an intensive time-domain reflectometry (TDR) sensor network in a log and surrounding soil within a northern hardwood forest in New England, United States. Intensive monitoring during a partial growing season indicated that deadwood moisture was dynamic but similar to that of surrounding soils at 15-min intervals, especially during wetting and drying events. Field results and bench analysis of the sample log revealed numerous challenges when attempting to monitor deadwood moisture with TDR such as heterogeneous and (or) advanced decay confounding TDR moisture measurements in logs. An efficient, high-frequency TDR sensor network was demonstrated to record deadwood and soil moisture fluctuations, which provides an opportunity to refine our understanding of deadwood dynamics in the context of global change such as changing precipitation regimes.more » « less
-
null (Ed.)Regulations that standardize the evaluation of wood-fired hydronic heaters (WHH) use mass loss as an important variable to compute energy input. Generally, mass loss is measured by placing the entire appliance on a scale and measuring the system mass change. This method suffers from resolution problems since the change in mass of the fuel during a run is much smaller than the total mass of the empty appliance. This experimental study provides a higher-resolution measurement of mass loss by measuring the concentration of flue gas emissions in addition to the flow rate of air into the WHH. Three fuels (red oak, cherry, and pine) are independently tested, and mea-surements of the emissions are made using both a Testo gas analyzer and tunable diode laser absorption spec-troscopy. A simultaneous direct measurement of the mass loss is performed using a hanging basket inside the WHH, and the average percent difference between the two methods are 5.4% for red oak, 5.4% for cherry, and 8% for pine, indicating that the emissions-based method is suitable for mass loss measurementsmore » « less
-
Neoclytus acuminatus acuminatus, the red-headed ash borer, is a wood-boring longhorn beetle (Cerambycidae: Cerambycinae) native to North America and introduced in Eurasia and South America. Its larvae develop in dying or recently dead hardwood trees, including ecologically and economically significant species of ash, hickory, and oak. We sequenced, assembled, and annotated the genome of a female N. acuminatus and compared it to the publicly available genomes of other cerambycid species. The 508 Mb N. acuminatus genome assembly spanned 20 contigs (19 nuclear + 1 mitochondrial), with an N50 of 52.59 Mb and largest contig of 61.20 Mb. A moderately high fraction of the genome (62.63%) comprised repetitive sequences, with nearly all (99.4%) expected single-copy orthologous genes (BUSCOs) present and fully assembled. We identified 2 contigs as fragments of the N. acuminatus sex chromosome. Genome annotation identified 12,899 genes, including 109 putative horizontally transferred loci. Synteny analysis identified well-conserved blocks of collinearity between the N. acuminatus genome and other Cerambycidae. The genome contains a similar number of genes encoding putative plant cell wall degrading enzymes as other Cerambycidae. The N. acuminatus genome provides new insights into genome evolution in the family Cerambycidae, known for its rich diversity of xylophagous species, and provides a new viewpoint from which to study the evolution and genomic basis of traits such as wood-feeding and olfaction in beetles and other insects.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/f11040479
