Font Size:
Integrating Sentinel-2 and PlanetScope Image with Drone-based Seagrass Data for Seagrass Percent Cover Mapping
Last modified: 2022-12-26
Abstract
Seagrass field data collection to train and assess remote sensing images for seagrass percent cover (PC) mapping can be laborious, costly, and time-consuming. There is also a potential information discrepancy between field seagrass data (0.25m2 or 1m2) and the spatial resolution of the image used. PlanetScope and Sentinel-2 are the frequently used images to map seagrass, and there is a considerable information gap between field seagrass data and their spatial resolution. Alternatively, the drone-based aerial image (drone data) can be used to interpret seagrass PC at similar level of precision to the remote sensing data used. This research assessed the integration of drone-based seagrass data with PlanetScope and Sentinel-2 images to map seagrass PC. Seagrass PC was interpreted from drone data for each 9m2 and 100m2 ground size following the PlanetScope and Sentinel-2 grids, respectively. Stepwise, random forest, and support vector regression were employed to develop the seagrass PC mapping model. The accuracy assessment of the resulting seagrass PC map involves the calculation of RMS error and plot 1:1 and its derivative analyses. Finally, this research provided insight into how drone data can be integrated with spaceborne remote sensing images for seagrass PC mapping effectively and efficiently.