Mapping of Shorea kunstleri King (Critically Endangered Species) Within Lambir Hills National Park
Shorea kunstleri King is one of the tree species that has been categorized by the International Union for Conservation of Nature (IUCN) as facing an extremely high risk of extinction in the wild. The importance to monitor the population of endangered tree species is to make sure that species receive...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | http://ir.unimas.my/id/eprint/40153/3/Thesis%20Master_DAYANG%20RAFIEDAH%20-%2024pages.pdf http://ir.unimas.my/id/eprint/40153/6/Dayang%20Rafiedah%20Awang%20Rapiee%20ft.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Shorea kunstleri King is one of the tree species that has been categorized by the International Union for Conservation of Nature (IUCN) as facing an extremely high risk of extinction in the wild. The importance to monitor the population of endangered tree species is to make sure that species receive continuous protection and assistance. This study was conducted at Lambir Hills National Park located in Miri, Sarawak. It is a mixed dipterocarp forest that has high species composition diversity in the area. Despite all that, there is a species that is critically endangered which is Shorea kunstleri King. The information on the distribution of Shorea kunstleri King can be used to assist conservation management. Therefore, remote sensing technology is incorporated into this study to facilitate the process of species identification. An airborne hyperspectral image mosaic was utilised in the research to evaluate the ability of this high spectral fidelity dataset with two types of classifiers Support Vector Machine (SVM) and Maximum likelihood (ML) to detect and map a tree species of interest (Shorea kunstleri King) within the mixed dipterocarp forest stand of the Lambir Hills National Park. In this study, two types of feature extraction Principal Component Analysis (PCA) and Spectral Derivative (SD) were applied to the classifiers. To demonstrate the effect, hyperspectral images with no feature extraction were classified using SVM and ML classifiers. The accuracies achieved from different feature extraction and classifiers were compared statistically. Based on the results, the image classified using SVM classifier achieved the most accurate characterisation with and without feature extraction compared to ML classifier. SVM classifier is known for its ability to generalise well even with limited training samples and is commonly used in image classification. The Kernel parameter in SVM classifier alongside feature extraction significantly affects the classification accuracy. The accuracy results from ML classification without feature extraction acquired poor classification. Therefore, feature extraction does affect the classification accuracy, but it depends on the morphology of the study area. It can be concluded that the SVM method with SD feature extraction could detect tree crowns of Shorea kunstleri with a Kappa coefficient of 0.8126 which showed a great agreement with the observed samples and overall accuracy of 89.89% that shows the accuracy of the final map.
Keywords: Classification, feature extraction, remote sensing, species identification, SVM |
|---|