Issue |
BIO Web Conf.
Volume 168, 2025
The 2nd International Seminar on Ocean Sciences and Sustainability (ISOSS 2024)
|
|
---|---|---|
Article Number | 05014 | |
Number of page(s) | 11 | |
Section | Sustainable Ocean Technology | |
DOI | https://doi.org/10.1051/bioconf/202516805014 | |
Published online | 10 April 2025 |
Assessing benthic habitat distribution in Tunda Island, Banten, Indonesia using Sentinel-2A imagery
1 Indonesian Coral Reef Foundation (Yayasan TERANGI), Jalan Asyibaniyah No. 105 – 106 Pondok Jaya Cipayung Depok Jawa Barat 16438
2 Department of Marine Science, Faculty of Science and Technology State Islamic, Universitas Islam Negeri Sunan Ampel Surabaya, East Java, Indonesia
* Corresponding author: fakhrurrozi@terangi.or.id
Benthic habitats in coastal areas are composed of diverse organisms and substrates such as seaweed, seagrass, algae, hard corals, dead corals, rock, and rubble. Understanding their distribution is essential for effective marine spatial planning and conservation. This study aimed to assess benthic habitat distribution around Tunda Island using Sentinel-2A satellite imagery and evaluate the classification accuracy. Field data were collected from March 5 to 7, 2024, using the photo transect method to identify key benthic classes. Image classification was performed using a Random Forest classifier, and accuracy was evaluated through a confusion matrix. The analysis identified four main benthic habitat classes: rock, rubble, seagrass, and hard coral. Habitat distribution generally followed a pattern across all stations—rock and rubble nearshore, transitioning to seagrass and hard coral further offshore. The areal coverage for each class was estimated as rock (31.89 ha), hard coral (31.29 ha), rubble (21.34 ha), and seagrass (11.99 ha). The classification achieved an overall accuracy of 69.86%, indicating that Sentinel-2A imagery combined with Random Forest classification holds promise for mapping benthic habitats in coastal environments like Tunda Island.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.