How canopy shadow affects invasive plant species classification in high spatial resolution remote sensing

Abstract

Plant invasions can result in serious threats for biodiversity and ecosystem functioning. Reliable maps at very‐high spatial resolution are needed to assess invasions dynamics. Field sampling approaches could be replaced by unmanned aerial vehicles (UAVs) to derive such maps. However, pixel‐based species classification at high spatial resolution is highly affected by within‐canopy variation caused by shadows. Here, we studied the effect of shadows on mapping the occurrence of invasive species using UAV‐based data. MaxEnt one‐class classifications were applied to map Acacia dealbata, Ulex europaeus and Pinus radiata in central‐south Chile using combinations of UAV‐based spectral (RGB and hyperspectral), 2D textural and 3D structural variables including and excluding shaded canopy pixels during model calibration. The model accuracies in terms of area under the curve (AUC), Cohen's Kappa, sensitivity (true positive rate) and specificity (true negative rate) were examined in sunlit and shaded canopies separately. Bootstrapping was used for validation and to assess statistical differences between models. Our results show that shadows significantly affect the accuracies obtained with all types of variables. The predictions in shaded areas were generally inaccurate, leading to misclassification rates between 65% and 100% even when shadows were included during model calibration. The exclusion of shaded areas from model calibrations increased the predictive accuracies (especially in terms of sensitivity), decreasing false positives. Spectral and 2D textural information showed generally higher performances and improvements when excluding shadows from the analysis. Shadows significantly affected the model results obtained with any of the variables used, hence the exclusion of shadows is recommended prior to model calibration. This relatively easy pre‐processing step enhances models for classifying species occurrences using high‐resolution spectral imagery and derived products. Finally, a shadow simulation showed differences in the ideal acquisition window for each species, which is important to plan revisit campaigns.

Automatic Windthrow Detection Using Very-High-Resolution Satellite Imagery and Deep Learning

“…Apparently, this is one of the important limitations associated with identifying the outfalls of individual trees and clarifying the boundaries of windthrow patches. If, in the case of unmanned aerial vehicles' shadows, their related problems can be effectively minimized [72], then for satellite imagery, one should pay attention to the choice of images taking into account the angle of sunlight incidence. We can also assume that the dissected relief and presence of heavily shaded slopes of the northern exposures (in the northern hemisphere) and southern slopes (in the southern hemisphere) are factors significantly impacting the algorithm outputs as well the pixel-based methods of deciphering remote sensing data.…”

Hypertemporal Imaging Capability of UAS Improves Photogrammetric Tree Canopy Models

“…Applying an NIR or red edge spectral band as master or sole camera when studying canopy structure or change detection in orthomosaic products of complex canopies appears to improve reconstruction of target features. Low solar elevations are typically avoided in remote sensing, with solar noon targeted to reduce shadow and improve radiometry (e.g., [57,58]). It has been previously demonstrated at lower spatial resolutions that reconstruction is possible at low solar elevations for large-format digital imagery [59].…”

Taking a closer look at invasive alien plant research: A review of the current state, opportunities, and future directions for UAVs

“…These means are skewed by a single rotary‐wing study that used unusually coarse imagery (GSD = 18 cm) (Wu et al, ), excluding this study, the average GSD collected with rotary‐wing craft was 4 cm. Only rotary‐wing craft have been deployed with a laser scanner (Dash et al, ) or hyperspectral cameras (Lopatin, Dolos, Kattenborn, & Fassnacht, ), but multispectral and RGB cameras have been used with both craft types. This is due to the greater flexibility, stability and capacity for lower velocity flight of the rotary‐wing craft.…”

“…Six studies used RGB imagery (Bryson et al, ; Hill et al, ; Mafanya et al, , ; Perroy et al, ; Wu et al, ) with the remainder using multispectral imagery with bands frequently including the near‐infrared and red edge. Only two studies (Kattenborn, Lopatin, Förster, Braun, & Fassnacht, ; Lopatin et al, ) used UAV‐borne hyperspectral imagery, but this will likely increase as miniaturized hyperspectral cameras become more accessible. A range of consumer‐grade RGB cameras have been used (Table ) and modifying consumer‐grade cameras by replacing the inbuilt filtre to capture broadband near‐infrared data has been popular (Table ).…”