Optimized Benthic Habitat Mapping with Sentinel-2: Integrating Lyzenga Correction and Hybrid Classification

DOI

10.2991/978-94-6463-920-9_8How to use a DOI?

Keywords

Benthic Habitat Mapping; Sentinel-2; Lyzenga Correction; Water Column Correction; Marine Protected Area; Baluran National Park

Abstract

This study presents a high-precision method for benthic habitat mapping in Bama Bay, Baluran National Park, by integrating Lyzenga’s water column correction with Sentinel-2 MSI data. Using Level-1C imagery (10-m resolution bands B2, B3, and B4), we applied Dark Object Subtraction (DOS) radiometric correction and calculated Lyzenga's attenuation coefficients to minimize water column effects. A hybrid classification approach combined unsupervised clustering (10 classes) with field-validated supervised classification of four benthic habitats: coral reef, macroalgae, seagrass, and sand. Field surveys along 274 validation points yielded an overall accuracy of 72.99% (exceeding Indonesia’s SNI 7716:2011 standard), with seagrass showing the highest user accuracy (90.37%). Habitat distribution analysis revealed coral dominance (43.61% coverage), followed by macroalgae (26.13%), seagrass (22%), and sand (8.2%). The Lyzenga correction improved classification accuracy by 27%, particularly in shallow clear waters (<5m), though fragmented zones showed limitations due to Sentinel-2's resolution. This study establishes a replicable framework for tropical benthic mapping in marine protected areas, demonstrating Sentinel-2's utility when paired with tailored water column corrections. The results support conservation planning while highlighting the need for UAVs in mixed-habitat zones.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Igor Aviezena Eris
AU  - Inayatul Fikriyah
AU  - Maria Ekacarini Jayanimita
AU  - Nunung Nuring Hayati
AU  - I Made Satya Graha
PY  - 2025
DA  - 2025/12/15
TI  - Optimized Benthic Habitat Mapping with Sentinel-2: Integrating Lyzenga Correction and Hybrid Classification
BT  - Proceedings of the International Conference on Recent Innovations in Sustainable Engineering Solutions 2025 (ICONRISES 2025)
PB  - Atlantis Press
SP  - 69
EP  - 78
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-920-9_8
DO  - 10.2991/978-94-6463-920-9_8
ID  - Eris2025
ER  -