Classification of Tree Composition in the Forest Using Images from SENTINEL-2: A Case Study of Geomunoreum Forests Using NDVI Images

Abstract

Climate change may alter tree species’ distribution, which could impact on forest biodiversity. However, frequent and continuous surveys of forests need intense labor and are time-consuming. The current study utilized SENTINEL-2 images of Geomunoreum to solve this problem as a case study. Acquired images were converted into various indices, such as the normalized difference vegetation index (NDVI), which could be an efficient method to examine the diversity in forests over time. In the current study, the images were obtained in March and April from 2017 to 2021. As a result of analysis using NDVI images of the study area taken from the satellite, vegetation groups were classified into evergreen trees and deciduous trees. This implies that NDVI using extracted data from SENTINEL-2 images could be used for surveying large-scale examinations for tree classification in order to observe variations caused by climate change in an efficient and cost-effective manner.

Keywords

• image analysis
• remote sensing
• RGB image
• satellite image
• vegetation survey