Abstract
Data on the distribution of tree species are often requested by forest managers, inventory agencies, foresters as well as private and municipal forest owners. However, the automated detection of tree species based on passive remote sensing data from aerial surveys is still not sufficiently developed to achieve reliable results independent of the phenological stage, time of day, season, tree vitality and prevailing atmospheric conditions. Here, we introduce a novel tree species classification approach based on high resolution RGB image data gathered during automated UAV flights that overcomes these insufficiencies. For the classification task, a computationally lightweight convolutional neural network (CNN) was designed. We show that with the chosen CNN model architecture, average classification accuracies of 92% can be reached independently of the illumination conditions and the phenological stages of four different tree species. We also show that a minimal ground sampling density of 1.6 cm/px is needed for the classification model to be able to make use of the spatial-structural information in the data. Finally, to demonstrate the applicability of the presented approach to derive spatially explicit tree species information, a gridded product is generated that yields an average classification accuracy of 88%.
Highlights
Forests provide crucial ecosystem services such as biomass production, air purification, and carbon storage
We show that with the chosen convolutional neural network (CNN) model architecture, average classification accuracies of 92% can be reached independently of the illumination conditions and the phenological stages of four different tree species
It should be noted that the best model performance did not necessarily occur after epoch 50, but often earlier with the earliest peak performance occurring after epoch 38. These results show that the chosen model architecture is essentially very well suited to differentiate the tree species treated in this study on the basis of simple RGB images
Summary
Forests provide crucial ecosystem services such as biomass production, air purification, and carbon storage Their efficiency and resilience is closely linked to tree species richness [1]. To meet the growing demand for spatially explicit data on the distribution of tree species, several classification approaches based on a variety of satellite data were proposed [6,7,8,9,10]. Since these data have a relatively coarse spatial resolution, they are, not well suited for classifying tree species at single-tree-level in complexly structured species-rich forests. As they are often dependent on expensive sensor technology, the economic viability of the approaches is not always guaranteed [5]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
