Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 54 min ago
Peer-reviewedCC BY 4.0Earth and Space Science

Object Detection of Tree Uprooting Signatures in Gridded LiDAR Elevation Data

  • T. H. Doane1,2,3
  • A. Agarwal4
  • B. J. Yanites2
  • D. A. Edmonds2
4 affiliations
  1. 1Desert Research Institute Las Vegas NV USA
  2. 2Earth and Atmospheric Sciences Indiana University Bloomington Bloomington IN USA
  3. 3Case Western Reserve University Cleveland OH USA
  4. 4Meta Platforms, Inc. Menlo Park CA USA
Open at sourcePDFDOICite

Abstract

Tree uprooting (or tree throw) is a natural forest disturbance with consequences for ecology, pedology, hydrology, geomorphology, and atmospheric fluxes. These events leave topographic signatures in the form of pit‐mound couplets (PMCs) that persist for decades to centuries. Therefore, the land surface serves as an archive of tree uprooting events. High resolution topographic data is capable of resolving many of these pit‐mound couplets, allowing us to access this archive. We have trained an object detection model, YOLOv5 (You Only Look Once), to automatically map PMCs in USGS 3D Elevation Program topographic data. The model achieves performance metrics of 0.76 for F1, 0.72 for precision, and 0.8 for recall. We field‐validate positive inferences and compare the predicted PMCs to those that we map in 0.25 m resolution LiDAR topographic data. We also provide a brief analysis of PMCs in Brown County, IN that demonstrates the spatial density of PMCs as a function of hillslope aspect and slope.

Related

  1. Explaining patterns learned by neural networks for detection of atmospheric surface fronts in gridded atmospheric data
    Tim Radke, Johanna Baehr, Marc Rautenhaus
    EGUspherePreprintCC BY 4.0General earth scienceEGUsphere
  2. Line‐Based Levee Detection: A New Generation of Levee Detection Methods Using Digital Elevation Models
    Do Ngoc Khanh, Kazuma Shiraishi, Yu Yoshimura +1
    Earth and Space SciencePeer-reviewedCC BY 4.0Full textGeneral earth scienceCrossref
  3. Conditional reliability of gridded rainfall datasets in Nigeria
    Segun Ezekiel Akorede, Chioma Suzan Dibani
    EarthArXivPreprintPublisher termsFull textAtmospheric science & meteorologyClimate scienceEarthArXiv
  4. Machine learning emulators of dynamic global vegetation models for fast gridded carbon budget predictions
    Piyu Ke, Xiaofan Gui, Stephen Sitch +5
    arXivPreprintCC BY 4.0Full textAtmospheric science & meteorologyarXiv
  5. Data assimilation of coherent structures in parametric and gridded spaces: an idealized ocean eddy study
    Solène Dealbera, Stéphane Raynaud, Carlos Granero Belinchon +3
    Nonlinear Processes in GeophysicsPeer-reviewedCC BY 4.0Full textOceanography & cryosphereStatisticsHAL

Cite

BibTeXRIS
BibTeX
@article{doane2026object,
  title = {{Object Detection of Tree Uprooting Signatures in Gridded LiDAR Elevation Data}},
  author = {T. H. Doane and A. Agarwal and B. J. Yanites and D. A. Edmonds},
  journal = {Earth and Space Science},
  year = {2026},
  month = oct,
  doi = {10.1029/2025ea004894},
  url = {https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2025EA004894},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Object Detection of Tree Uprooting Signatures in Gridded LiDAR Elevation Data
AU  - T. H. Doane
AU  - A. Agarwal
AU  - B. J. Yanites
AU  - D. A. Edmonds
PY  - 2026
DA  - 2026/10/30
JO  - Earth and Space Science
DO  - 10.1029/2025ea004894
UR  - https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2025EA004894
AB  - Tree uprooting (or tree throw) is a natural forest disturbance with consequences for ecology, pedology, hydrology, geomorphology, and atmospheric fluxes. These events leave topographic signatures in the form of pit‐mound couplets (PMCs) that persist for decades to centuries. Therefore, the land surface serves as an archive of tree uprooting events. High resolution topographic data is capable of resolving many of these pit‐mound couplets, allowing us to access this archive. We have trained an object detection model, YOLOv5 (You Only Look Once), to automatically map PMCs in USGS 3D Elevation Program topographic data. The model achieves performance metrics of 0.76 for F1, 0.72 for precision, and 0.8 for recall. We field‐validate positive inferences and compare the predicted PMCs to those that we map in 0.25 m resolution LiDAR topographic data. We also provide a brief analysis of PMCs in Brown County, IN that demonstrates the spatial density of PMCs as a function of hillslope aspect and slope.
SN  - 2333-5084
SN  - 2333-5084
ER  -