Mapping Coral Reef Habitat Using High-Resolution Satellite Imagery and Temporally Disparate In Situ Data: A Multi-Depth Analysis Batrisyia Che Azani1, Nurul Ain Mohd Zaki2,3*, Mohd Zainee Zainal4, Rozaimi Che Hasan4 and Tajul Rosli Razak5,6
1Research assistant/ Postgraduate Students, Faculty of Built Environment, Universiti Teknologi MARA, Perlis Branch, Arau Campus, 02600 Arau, Perlis, Malaysia
2Senior lecturer, Faculty of Built Environment, Universiti Teknologi MARA, Perlis Branch, Arau Campus, 02600 Arau, Perlis, Malaysia
3Associate Fellow, Institute for Biodiversity and Sustainable Development, Universiti Teknologi MARA, Shah Alam, 40450, Malaysia
4Senior lecturer, School of Engineering and Technology, Jalan Sultan Yahya Petra, Universiti Teknologi Malaysia, 54100 Kuala Lumpur, Wilayah Persekutuan Kuala Lumpur, Malaysia
5Senior lecturer, College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Shah Alam, Malaysia
6Postdoctoral Researcher, Department of Architecture and Built Environment, University of Nottingham, United Kingdom
Abstract
Over the past few years, coral reefs have faced multiple threats from environmental and anthropogenic stressors. It is beyond doubt that monitoring coral reefs is crucial particularly for habitat changes detection. Despite that, matching the date for both satellite images with field data oftentimes can be challenging. Therefore, this study used Pleiades high-multi resolution satellite image of Pinang Island, Terengganu, Malaysia for coral reef habitat classification and in situ data from CPCe photo quadrats and underwater photographs collected in 2024 which are temporally delayed. The satellite image, limited to surface reflectance, was processed to extract spectral and texture indices. In situ data, including 376 georeferenced quadrats with depth and substrate composition from 40 locations, were integrated and stratified by depth (<5m and >5m) to assess classification performance across varying optical conditions. Furthermore, random forest algorithm classification will be applied as machine learning classifiers with underwater photographs as visual reference to address the four-year temporal gap. This approach aims to demonstrate how older satellite data can support coral reef mapping when recent or up-to-date imagery is unavailable through the integration with more recent field observations, from several years later.
