The doctoral dissertation in the field of Forestry will be examined at the Faculty of Science, Forestry and Technology, Joensuu campus.
What is the topic of your doctoral research? Why is it important to study the topic?
My doctoral research focuses on the use of uncrewed aerial vehicles (UAVs, or drones) for tree species classification and biodiversity monitoring in boreal forests. The study evaluates how different UAV sensor technologies, including RGB cameras, multispectral sensors, and LiDAR, can be used to identify tree species and ecologically important forest elements such as European aspen and standing dead trees.
The topic is important because accurate information on forest composition is essential for sustainable forest management, biodiversity conservation, and monitoring. Traditional forest inventories are often time-consuming and may overlook sparsely distributed but ecologically valuable species. UAV-based remote sensing provides a flexible and cost-effective way to collect detailed forest information at the individual-tree level. The results contribute to the development of more efficient forest inventory methods and improved monitoring of biodiversity in boreal forest ecosystems.
What are the key findings or observations of your doctoral research?
The research demonstrated that UAVs can accurately classify tree species and biodiversity-relevant forest elements at the individual-tree level in boreal forests. Depending on the sensor type and forest conditions, classification accuracies ranged from 79% to 95%. One of the key findings was that the timing of data acquisition strongly influences classification performance.
Data collected during early leaf development provided better discrimination of European aspen than data collected later in the growing season. The study also showed that spectral information from multispectral sensors was generally more important for species identification than structural information alone, although LiDAR data significantly improved tree detection and crown delineation.
Another important contribution was the successful detection of ecologically valuable but often overlooked biodiversity indicators, including European aspen and standing dead trees. These elements are difficult to identify using traditional forest inventory methods despite their importance for many forest species. The novelty of the work lies in the systematic comparison of different UAV sensor technologies, seasons, and classification approaches across multiple studies.
The results improve understanding of how drone-based remote sensing can support biodiversity monitoring and provide forest managers with more detailed and cost-effective information for conservation planning and sustainable forest management.
What are the key research methods and materials used in your doctoral research?
The research was conducted in boreal forests across Finland and combined field measurements with UAV-based remote sensing. Several UAVs equipped with RGB cameras, multispectral sensors, and LiDAR were used to collect high-resolution data on forest structure and tree canopies. The workflow included individual tree detection, crown delineation, extraction of spectral and structural features, and machine learning-based species classification. The analyses focused on ecologically important but relatively rare targets, such as European aspen and standing dead trees. Field measurements were used to validate the results and assess classification accuracy.
By comparing different sensors, seasons, and classification approaches, the research evaluated how data acquisition influences the identification of tree species and biodiversity indicators in boreal forests.
The doctoral dissertation of Anton Kuzmin, MSc, entitled Boreal forest tree species classification using uncrewed aerial vehicles will be examined at the Faculty of Science, Forestry and Technology, Joensuu campus. The opponent will be Professor Krzysztof Stereńczak, Forest Research Institute, Poland, and the custos will be Professor Matti Maltamo, University of Eastern Finland. Language of the public defence is English.
For further information, please contact:
Anton Kuzmin, [email protected], tel. +358 50 409 5878
