Effect of varied unmanned aerial vehicle laser scanning pulse density on accurately quantifying forest structure

ABSTRACT

Airborne laser scanning (ALS) is increasingly used to estimate various forest characteristics. Technological improvements in unmanned aerial vehicles (UAVs) and drone laser scanning (DLS) sensors have permitted the acquisition of high pulse density datasets. There is an assumption that higher pulse densities yield greater accuracies in estimating forest characteristics. In this study, we investigated the effect of pulse density (.25, .5, 1, 5, 10, 50, 100 and 300 pulses m⁻²) on the ability to delineate individual tree crowns (ITCs) and estimate ITC height and crown horizontal diameter, in addition to plot-level leaf area index (LAI). The current study took place in an experimentally varied Pinus taeda L. forest, which included three stem densities: (i) 618; (ii) 1236; and (iii) 1853 trees per hectare (TPH). ITCs were classified directly from the DLS point cloud for each of the pulse densities. The correct delineation of ITCs relative to field tree-coordinates was relatively consistent (±5%) for pulse densities of 5 to 300 pulses m⁻². ITC delineation accuracy decreased with lower pulse densities. Planting stem density did impact ITC delineation accuracy. Higher pulse densities, plots with 618 TPH correctly classified ~88% of ITCs, and plots with the 1853 TPH correctly classified ~50% of ITCs. Estimates of tree height were largely unaffected by changes in tree density. Root mean square error (RMSE) for tree height varied from .5 to 2.5 m at pulse densities of 300 to .25 pulses m⁻², respectively. Estimates of crown horizontal diameter varied with regard to both pulse and stem density from 1.2 (300 ppm⁻² and 1853 TPH) to 4.2 m (.25 ppm⁻² and 618 TPH). RMSE varied among stem densities from .6 to 1.2 m as pulse density decreased. There was significant difference in ITC delineation accuracy, particularly when considering stem density, and the estimates of tree height and crown horizontal diameter among the DLS pulse densities used. The accuracy of predicted LAI was largely unaffected by changes in pulse density, when pulse density was above .5 pulses m⁻². There was little or no difference in estimates of LAI at these pulse densities. Our results suggest that low-density DLS data may be capable of estimating plot-level forest metrics reliably in some situations, however once the analysis scale is reduced to the individual-tree-level, the influence of pulse density is more substantial. The results here provide guidance to forest managers who must balance metric estimation accuracy and price when planning new ALS or DLS acquisitions.

Keywords:

• LiDAR
• precision forestry
• LAI
• loblolly pine
• silviculture
• individual tree crown delineation
• remote sensing

Research highlights

• LiDAR pulse density and stem planting density influence individual tree crown delineation;

• Individual-tree-level estimates are more sensitive to pulse density than plot-level estimates;

• Above a pulse density of 0.5 pulses m⁻² LAI can be estimated with consistent accuracy;

• Higher pulse densities provided higher accuracy for individual-tree estimates.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

Data available on request from the authors. The data that support the findings of this study are available from the corresponding author, MJS, upon reasonable request.

Supplementary material

Supplemental data for this article can be accessed https://doi.org/10.1080/01431161.2021.2023229.

Additional information

Funding

This work was primarily funded by the Forest Productivity Cooperative. This work was also supported by the Virginia Agricultural Experiment Station (Critz, Virginia), and the USDA National Institute of Food and Agriculture, U.S. Department of Agriculture (Washington, DC, USA).