Thesis subject
MSc thesis topic: Tree species identification in complex tropical rainforest using UAV based multisensor approach
Tropical rainforest are highly complex ecosystem, characterize by biodiversity of flora and fauna. They also play a vital role in climate regulation through carbon sequestration and the carbon cycle (Zhou et al., 2013). The classification of individual tree species is also important for forest ecology as it supports biodiversity monitoring, invasive species identification and sustainable forest management (Fassnacht et al., 2016).
However, tree species identification in complex tropical rainforest is challenging due to the presence of large number of tree species, varying tree heights and heterogeneous canopies. Moreover, tree species identification in tropical rainforest is still underexplored and much focus has been given to boreal, temperate forest species.
Problem Statement
Tropical rainforest has high floristic diversity and it present difficulty in separating different tree species and the studies related to identification of tree species in tropical rainforest are very limited. Therefore, this study will serve as a framework for future studies involving tree species diversity and tropical forest management practices.
Objectives and Research questions
This study aims to tackle the challenge of tree species identification by taking advantage of the remote sensing technologies and will investigate the use of ultra-high resolution RGB and LiDAR data in identifying individual tree species in complex rainforest. The aim is also to combine remote sensing data from RGB and LiDAR for discriminating the tropical rainforest tree species. Following questions will be investigated:
- What kind of LiDAR derived features can help in identification of individual tree species in tropical rainforest?
- What kind of textural features can be useful in discriminating tree species?
- Does combining textural and LiDAR features further improve the identification of tree species?
Requirements
- Advance Earth Observation
- Machine Learning
- R and Python
Literature and information
- Fassnacht, F. E., Latifi, H., Stereńczak, K., Modzelewska, A., Lefsky, M., Waser, L. T., Straub, C., & Ghosh, A. (2016). Review of studies on tree species classification from remotely sensed data. In Remote Sensing of Environment (Vol. 186, pp. 64–87). Elsevier Inc.
- Zhou, X., Fu, Y., Zhou, L., Li, B., & Luo, Y. (2013). An imperative need for global change research in tropical forests. In Tree Physiology (Vol. 33, Issue 9, pp. 903–912).
Theme(s): Sensing & measuring