skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


This content will become publicly available on July 1, 2026

Title: Environmental Sensitivity in AI Tree Bark Detection: Identifying Key Factors for Improving Classification Accuracy
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
Award ID(s):
2412928
PAR ID:
10620550
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
MDPI Algorithms
Date Published:
Journal Name:
Algorithms
Volume:
18
Issue:
7
ISSN:
1999-4893
Page Range / eLocation ID:
417
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Forests)
    null (Ed.)
    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
  2. ; ; ; (, Environmental Data Initiative)
    Foliar chemistry values were obtained from two important native tree species (white oak (Quercus alba L.) and red maple (Acer rubrum L.)) across urban and reference forest sites of three major cities in the eastern United States during summer 2015 (New York, NY (NYC); Philadelphia, PA; and Baltimore, MD). Trees were selected from secondary growth oak-hickory forests found in New York, NY; Philadelphia, PA; and Baltimore, MD, as well as at reference forest sites outside each metropolitan area. In all three metropolitan areas, urban forest patches and references forest sites were selected based on the presence of red maple and white oak canopy dominant trees in patches of at least 1.5 hectares with slopes less than 25%, and well-drained soils of similar soil series within each metropolitan area. Within each city, several forest patches were selected to capture the variation in forest patch site conditions across an individual city. All reference sites were located in protected areas outside of the city and within intermix wildland-urban interface landscapes, in order to target similar contexts of surrounding land use and population density (Martinuzzi et al. 2015). Several reference sites were selected for each city, located within the same protected area considered representative of rural forests of the region. White oaks were at least 38.1 cm diameter at breast height (DBH), red maples were at least 25.4 cm DBH, and all trees were dominant or co-dominant canopy trees. The trees had no major trunk cavities and had crown vigor scores of 1 or 2 (less than 25% overall canopy damage; Pontius & Hallett 2014). From early July to early August 2015, sun leaves were collected from the periphery of the crown of each tree with either a shotgun or slingshot for subsequent analysis to determine differences in foliar chemistry across cities and urban vs. reference forest site types. The data were used to invstigate whether differences in native tree physiology occur between urban and reference forest patches, and whether those differences are site- and species-specific. A complete analysis of these data can be found in: Sonti, NF. 2019. Ecophysiological and social functions of urban forest patches. Ph.D. dissertation. University of Maryland, College Park, MD. 166 p. References: Martinuzzi S, Stewart SI, Helmers DP, Mockrin MH, Hammer RB, Radeloff VC. 2015. The 2010 wildland-urban interface of the conterminous United States. Research Map NRS-8. US Department of Agriculture, Forest Service, Northern Research Station: Newtown Square, PA. Pontius J, Hallett R. 2014. Comprehensive methods for earlier detection and monitoring of forest decline. Forest Science 60(6): 1156-1163. 
    more » « less
  3. ; (, Geophysical Research Letters)
    Abstract Understanding and predicting future consequences of increasingly frequent and intense droughts requires improved monitoring of forest response. Over the course of a day, tree mass and stiffness respond dynamically to changing atmospheric and hydraulic conditions. By conducting a 24‐hr experiment, we sought to disentangle the effects of changing mass and stiffness on tree sway period. We observed that tree mass and stiffness are influenced by changes in tree water content and that diurnal changes in tree sway period are chiefly driven by the loss and recovery of tree stiffness. Over a season‐long time series in twoQuercus rubra(red oak) trees, we observed more pronounced and substantially higher midday increases (+7%) in sway period during days with the driest soil moisture (<0.09) as compared to days when soils were wetter. These findings suggest that continuously monitoring tree sway period offers an innovative approach to detecting water stress in trees. 
    more » « less
  4. ; ; ; (, Tree Physiology)
    Abstract Understanding how mixed-species forests uptake subsurface water sources is critical to projecting future forest water use and stress. Variation in root water uptake (RWU) depths and volumes is common among trees but it is unclear how it is affected by species identity, local water availability or neighboring tree species compositions. We evaluated the hypothesis that RWU depths and the age of water (i.e., time since water entered soils as precipitation) taken up by red maples (Acer rubrum) varied significantly between two forested plots, both containing red maples, similar soils, topography and hydrologic conditions, but having different neighboring tree species. We measured soil moisture contents as well as stable isotopes (δ2H, δ18O) in plant xylem water and soil moisture across two years. These data were used to calibrate process-based stand-level ecohydrological models for each plot to estimate species-level RWU depths. Model calibration suggested significant differences in red maple tree RWU depths, transpiration rates and the ages of water taken up by maples across the two stands. Maple trees growing with ash and white spruce relied on significantly deeper and older water from the soil profile than maple trees growing with birch and oak. The drought risk profile experienced by maple trees differed between the plots as demonstrated by strong correlations between precipitation and model simulated transpiration on a weekly time scale for maples taking up shallow soil moisture and a monthly time scale for maples reliant on deeper soil moisture. These findings carry significant implications for our understanding of water competition in mixed-species forests and for the representation of forest rooting strategies in hydrologic and earth systems models. 
    more » « less
  5. ; ; ; (, Soil Science Society of America Journal)
    Abstract Microbial biomass is known to decrease with soil drying and to increase after rewetting due to physiological assimilation and substrate limitation under fluctuating moisture conditions, but how the effects of changing moisture conditions vary between dry and wet environments is unclear. Here, we conducted a meta‐analysis to assess the effects of elevated and reduced soil moisture on microbial biomass C (MBC) and microbial biomass N (MBN) across a broad range of forest sites between dry and wet regions. We found that the influence of both elevated and reduced soil moisture on MBC and MBN concentrations in forest soils was greater in dry than in wet regions. The influence of altered soil moisture on MBC and MBN concentrations increased significantly with the manipulation intensity but decreased with the length of experimental period, with a dramatic increase observed under a very short‐term precipitation pulse. Moisture effect did not differ between coarse‐textured and fine‐textured soils. Precipitation intensity, experimental duration, and site standardized precipitation index (dry or wet climate) were more important than edaphic factors (i.e., initial water content, bulk density, and clay content) in determining microbial biomass in response to altered moisture in forest soils. Different responses of microbial biomass in forest soils between dry and wet regions should be incorporated into models to evaluate how changes in the amount, timing, and intensity of precipitation affect soil biogeochemical processes. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email