Skip to main content
ARS Home » Pacific West Area » Logan, Utah » Forage and Range Research » Research » Publications at this Location » Publication #398550
Research Project: Improved Plant Genetic Resources and Methodologies for Rangelands, Pastures, and Turf Landscapes in the Semiarid Western U.S.

Location: Forage and Range Research

Title: Mapping floral resources in montane landscapes using unmanned aerial systems and two-step random forest classifications

Author
item TABOR, JESSE - Utah State University
item Hernandez, Alexander
item Cox-Foster, Diana
item Love, Byron
item McCabe, Lindsie
item Koch, Jonathan
item Robbins, Matthew

Submitted to: Rangeland Ecology and Management
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/30/2024
Publication Date: 8/14/2024
Citation: Tabor, J., Hernandez, A.J., Cox-Foster, D.L., Love, B.G., Mccabe, L.M., Koch, J., Robbins, M.D. 2024. Mapping floral resources in montane landscapes using unmanned aerial systems and two-step random forest classifications. Rangeland Ecology and Management. 98:223-236. https://doi.org/10.1016/j.rama.2024.06.016.
DOI: https://doi.org/10.1016/j.rama.2024.06.016

Interpretive Summary: Flowers provide many ecosystem services such as food for insect pollinators, they enhance recreational landscapes, and the resulting fruits and seeds from flowers are essential for the survival of many animal species. There is a growing need for several stakeholders such as bee keepers, scientists, and land managers to obtain accurate spatial estimates of floral resources in natural, non-agricultural settings. Maps of flower on the landscape provide not only biodiversity indicators but also give a good idea of the quantity and quality of resources that are available for pollinators.

Technical Abstract: Monitoring floral biodiversity is a critical step in understanding terrestrial ecosystems. However, manual methods to quantify flowering vegetation are costly in time and personnel. In large landscapes, these limited methods may not capture the spatial and temporal variation of floral resources. Recent advances in sensors and unmanned aerial vehicle (UAV) platforms offer opportunities to characterize the dynamic distribution of floral resources at the landscape level. In this study, UAV imagery and a multistep machine learning classification analysis were used to quantify floral resources in nonagricultural environments, where topography, vegetation, and inflorescence size were variable. Seven flowering species covering an area of 2 138 m2 were classified throughout our study, equaling 0.5% of the overall landscape. We determined the period of flowering for important species based on the temporal changes of the floral area classified from UAV images. Models performed well considering the extreme rarity of flowers in the UAV images. The flower class in the land cover classification models performed well with an average sensitivity of 0.77 and average specificity of 0.99. Individual flower classes also performed well with the majority of flower classes receiving sensitivity and specificity values of over 0.90. The use of UAVs is a feasible method for characterizing floral resources in nonagricultural settings. Classifications would benefit from a more robust and comprehensive UAV and floral resource sampling plan, to better characterize the variability of floral resources in UAV imagery.