Paper
2 November 2017 Comparison of different discriminant functions for mangrove species analysis in Matang Mangrove Forest Reserve (MMFR), Perak based on statistical approach
Author Affiliations +
Abstract
Mangroves are known as salt-tolerant evergreen forests, whereas its create land-ocean interface ecosystems. Besides, mangroves bring direct and indirect benefits to human activities and play a major role as significant habitat for sustaining biodiversity. However, mangrove ecosystem study based on the mangrove species are very crucial to get a better understanding of their characteristics and ways to separate among them. In this paper, discriminant functions obtained using statistical approach were used to generate the score range for six mangrove species (Rhizophora apiculata, Acrostichum aurem, Acrostichum speciosum, Acanthus ilicifolius, Ceriops tagal and Sonneratia ovata) in Matang Mangrove Forest Reserve (MMFR), Perak. With the computation of score range for each species, the fraction of the species can be determined using the proposed algorithm. The results indicate that by using 11 discriminant functions out of 16 are more effective to separate the mangrove species as the higher accuracy was obtained. Overall, the determination of leaf sample’s species is chosen base on the highest fraction measured among the six mangrove species. The obtained accuracy for mangrove species using statistical approach is low since it is impossible to successfully separate all the mangrove species in leaf level using their inherent reflectance properties. However, the obtained accuracy results are satisfactory and able to discriminate the examined mangrove species at species scale.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Boon Chun Beh, Kok Chooi Tan, Mohd. Zubir Mat Jafri, and Hwee San Lim "Comparison of different discriminant functions for mangrove species analysis in Matang Mangrove Forest Reserve (MMFR), Perak based on statistical approach", Proc. SPIE 10421, Remote Sensing for Agriculture, Ecosystems, and Hydrology XIX, 104211U (2 November 2017); https://doi.org/10.1117/12.2277821
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Reflectivity

Statistical analysis

Ecosystems

Algorithm development

Forestry

Short wave infrared radiation

Earth observing sensors

Back to Top