Day 4

Detailed paper information

Back to list

Paper title Multi-sensor UAS-based approach for European Aspen detection in boreal forest
  1. Anton Kuzmin University of Eastern Finland Speaker
  2. Lauri Korhonen University of Eastern Finland
  3. Pasi Korpelainen University of Eastern Finland
  4. Topi Tanhuanpää University of Eastern Finland
  5. Janne Mäyrä Finnish Environment Institute (SYKE)
  6. Matti Maltamo University of Eastern Finland
  7. Petteri Vihervaara Finnish Environment Institute SYKE
  8. Timo Kumpula University of Eastern Finland
Form of presentation Poster
  • C4. HAPs/UAVs
    • C4.01 Innovative UAV applications
Abstract text Mixed-species forests can host greater species richness and provide more important ecosystem services compared to monocultures of conifers. In boreal environments, particularly old deciduous trees have been recognized to promote species richness. Accurate identification of tree species is thus essential for effective mapping and monitoring of biodiversity and sustainable forest management. European aspen (Populus tremula L.) is a keystone species for the biodiversity of boreal forest. Large-diameter aspens maintain the diversity of hundreds of species, many of which are threatened in Fennoscandia. Majority of the classification studies so far focused on the dominant tree species, with fewer studies on less frequent but ecologically important species. Due to a low economic value and relatively sparse and scattered occurrence of aspen in boreal forests, there is a lack of information of the spatial and temporal distribution of aspen.

In this study, we assessed the potential of an RGB, Multispectral (MSP) and Hyperspectral (HS) UAS-based sensors and its combination for identification of European aspen at individual tree level using different combinations of spectral and structural features derived from high-resolution photogrammetric RGB and MSP point clouds and HS orthomosaics. Moreover, we included a standing deadwood as a separate class into the classification analysis to assess the possibilities to recognize it among the main tree species, because along with aspens, standing deadwood plays a significant role in maintaining biodiversity in a boreal forest.

We aimed to find out if a single sensor solution is more efficient than the combination of multiple data sources for efficient planning and implementation of sustainable forest management practices using the UAS-based approach. Experiments were conducted using >1000 ground measured trees in a southern boreal forest mainly consisting of Scots pine (Pinus sylvestris L.), Norway spruce (Picea abies (L.) Karst), silver birch (Betula pendula) and downy birch (Betula pubescens L.) together with 200 standing deadwood trees. The proposed method provides a new possibility for the rapid assessment of aspen occurrence to enable more efficient forest management as well as contribute to biodiversity monitoring and conservation efforts in a boreal forest.