Remote Sensing Image for Habitat Classification and Water Depth Estimation in Coastal Area

Project Details


Because of the wide area and sailing inconvenience caused by reef patches in lagoon, the Dongsha Atoll have not complete surveyed for a long time. The investigation is not conducive to the traditional characteristics but just suitable for satellite images of large scale investigation. This study focuses on the ecological environment of Dongsha ocean national park, investigates the influence of natural and artificial disturbances on coral habitats and the recovery and the ability to adapt. This subproject used multi-spectral optical satellite images cooperated with in situ ground truth data, to investigate the habitat distribution of sea grass and live coral, and estimate the area. The accuracy evaluation of the habitats survey with ground truthing can reach 80% accuracy. The satellite images from different seasons indicate seasonal changes of the sea grass and algae. Furthermore, thermal images from satellite can also provide information to estimate sea surface temperature and observe global warming phenomenon. Recently developed Unmanned Aerial Vehicle (UAV) will be adopted to take aerial images with high resolution. It can monitor test areas with high temporal density and bridge the satellite images and ground surveys.In this 3-year subproject, the selected test sites in Dongsha Atoll are monitored by satellite images. Combine the ground truth data collected with other subprojects, the result will be applied to the whole atoll. In the first year, satellite images with visible bands are used to monitor the coral reef and sea grass habitat, and the changes in area. Especially the recovery of the sea grass which disappear for 30 Km2 in north crest around July in 2014 and 2015. In the second year, UAV will be the bridge between the satellite images and ground surveys test sites for the changes of coral, sea grass and algae. The classification results will also be applied to water depth estimation with physical and empirical models. Finally in the third year, thermal band of satellite image will be adopted for sea surface temperature estimation. Combine with the water quality, salinity and temperature measured on site, it may provide reason for the sea grass disappearance the Dongsha Atoll. The approach can further be applied to the South China Sea.
Effective start/end date1/08/1831/08/19

UN Sustainable Development Goals

In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):

  • SDG 6 - Clean Water and Sanitation
  • SDG 14 - Life Below Water
  • SDG 17 - Partnerships for the Goals


  • Satellite Image
  • Bathymetry Estimation
  • Habitat Classification
  • Unmanned Aerial Vehicle (UAV)
  • Sea Surface Temperature.


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.