SUPERVISED IMAGE CLASSIFICATION MODEL FOR CORAL BLEACHING DETECTION USING A BI-TEMPORAL SENTINEL-2 IMAGE STACK
Open Access
- 25 April 2024
- journal article
- research article
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLVIII-4/W, 395-401
Abstract
Coral reefs are among the most vulnerable ecosystems to coastal and land-based anthropogenic factors. Aside from sudden increase in sea temperatures, external factors such as local and regional disturbances are found to influence coral reef environments which often lead to bleaching events. According to the Status of Coral Reefs of the World: 2020 report, from 2009 to 2018, there has been a progressive loss of live corals at the global level which may be attributed to the increasing anthropogenic activities (Souter et al., 2021). Due to coral’s sensitivity to environmental stressors, it is significantly considered as an indicator for global climate conditions. In this regard, this study developed a remote sensing change detection technique to segment coral bleaching from satellite images. Using a bi-temporal image stack composed of Sentinel-2 images showing pre and post bleaching, a machine learning classification model was developed to capture typologies of changes visible between the two images which included bleaching. Random Forest (RF) algorithm was employed to classify changes. This model obtained overall accuracies and kappa statistics of 0.97 and 0.94 respectively with minimum consumer and producer accuracy of 0.91. Moreover, the identified changes showed 78% agreement with the in-situ data composed of 31 monitoring stations distributed around Sekisei Lagoon, Okinawa, Japan. This study demonstrated a promising potential of machine learning for change detection for coral bleaching monitoring.Keywords
This publication has 22 references indexed in Scilit:
- Identification of coral spawn source areas around Sekisei Lagoon for recovery and poleward habitat migration by using a particle-tracking modelScientific Reports, 2021
- The potency of Sentinel-2 satellite for monitoring during and after coral bleaching events of 2016 in the some islands of Marine Recreation Park (TWP) of Pieh, West SumatraIOP Conference Series: Earth and Environmental Science, 2019
- Coral reef applications of Sentinel-2: Coverage, characteristics, bathymetry and benthic mapping with comparison to Landsat 8Remote Sensing of Environment, 2018
- Google Earth Engine: Planetary-scale geospatial analysis for everyoneRemote Sensing of Environment, 2017
- Assessment of coral bleaching using symbiotic zooxanthellae density and satellite remote sensing data in the Nansha Islands, South China SeaChinese Science Bulletin, 2011
- Detection limits of coral reef bleaching by satellite remote sensing: Simulation and data analysisRemote Sensing of Environment, 2004
- Coral reef habitat discrimination using multivariate spectral analysis and satellite remote sensingInternational Journal of Remote Sensing, 2003
- Change detection in shallow coral reef environments using Landsat 7 ETM+ dataRemote Sensing of Environment, 2001
- Coral reef habitat mapping: how much detail can remote sensing provide?Marine Biology, 1997
- The use of the Normalized Difference Water Index (NDWI) in the delineation of open water featuresInternational Journal of Remote Sensing, 1996