From UAV to PlanetScope: Upscaling fractional cover of an invasive species Rosa rugosa

Thaísa F Bergamo; Raul Sampaio de Lima; Tiiu Kull; Raymond D Ward; Kalev Sepp; Miguel Villoslada

doi:10.1016/j.jenvman.2023.117693

From UAV to PlanetScope: Upscaling fractional cover of an invasive species Rosa rugosa

J Environ Manage. 2023 Jun 15:336:117693. doi: 10.1016/j.jenvman.2023.117693. Epub 2023 Mar 11.

Authors

Thaísa F Bergamo¹, Raul Sampaio de Lima², Tiiu Kull², Raymond D Ward³, Kalev Sepp², Miguel Villoslada⁴

Affiliations

¹ Institute of Agriculture and Environmental Sciences, Estonian University of Life Sciences, Kreutzwaldi 5, EE-51006, Tartu, Estonia; Department of Geographical and Historical Studies, University of Eastern Finland, P.O. Box 111, FI-80101, Joensuu, Finland. Electronic address: thaisafbergamo@gmail.com.
² Institute of Agriculture and Environmental Sciences, Estonian University of Life Sciences, Kreutzwaldi 5, EE-51006, Tartu, Estonia.
³ Institute of Agriculture and Environmental Sciences, Estonian University of Life Sciences, Kreutzwaldi 5, EE-51006, Tartu, Estonia; Centre for Aquatic Environments, School of the Environment and Technology, University of Brighton, Cockcroft Building, Moulsecoomb, Brighton, BN2 4GJ, UK.
⁴ Institute of Agriculture and Environmental Sciences, Estonian University of Life Sciences, Kreutzwaldi 5, EE-51006, Tartu, Estonia; Department of Geographical and Historical Studies, University of Eastern Finland, P.O. Box 111, FI-80101, Joensuu, Finland.

PMID: 36913856
DOI: 10.1016/j.jenvman.2023.117693

Abstract

Invasive plant species pose a direct threat to biodiversity and ecosystem services. Among these, Rosa rugosa has had a severe impact on Baltic coastal ecosystems in recent decades. Accurate mapping and monitoring tools are essential to quantify the location and spatial extent of invasive plant species to support eradication programs. In this paper we combined RGB images obtained using an Unoccupied Aerial Vehicle, with multispectral PlanetScope images to map the extent of R. rugosa at seven locations along the Estonian coastline. We used RGB-based vegetation indices and 3D canopy metrics in combination with a random forest algorithm to map R. rugosa thickets, obtaining high mapping accuracies (Sensitivity = 0.92, specificity = 0.96). We then used the R. rugosa presence/absence maps as a training dataset to predict the fractional cover based on multispectral vegetation indices derived from the PlanetScope constellation and an Extreme Gradient Boosting algorithm (XGBoost). The XGBoost algorithm yielded high fractional cover prediction accuracies (RMSE = 0.11, R² = 0.70). An in-depth accuracy assessment based on site-specific validations revealed notable differences in accuracy between study sites (highest R² = 0.74, lowest R² = 0.03). We attribute these differences to the various stages of R. rugosa invasion and the density of thickets. In conclusion, the combination of RGB UAV images and multispectral PlanetScope images is a cost-effective method to map R. rugosa in highly heterogeneous coastal ecosystems. We propose this approach as a valuable tool to extend the highly local geographical scope of UAV assessments into wider areas and regional evaluations.

Keywords: Baltic; Coast; Estonia; Invasive species; Machine learning; Rosa rugosa; Satellite; Unoccupied aerial vehicles.

MeSH terms

Biodiversity
Ecosystem
Introduced Species*
Plants
Rosa*