Improving the synoptic mapping of coral reef geomorphology using object-based image analysis

Abstract

Monitoring coral reefs is of great importance for environmental management of these ecosystems. The use of remote sensing and geographical information systems enables rapid and effective mapping of the geomorphology of reefs that can be used as a basis for biodiversity and habitat assessments. However, pixel-based approaches have not been appropriate for detailed mapping of such complex systems. An object-based image analysis (OBIA) approach was used in this study to map intra-reef geomorphology of coral reefs across the Torres Strait region using Landsat ETM+ imagery. By combining image analysis techniques and a non-parametric neural network classifier and incorporating additional spatial information such as context, shape and texture, the accuracy of the segmentation and classification was improved considerably. A large-scale synoptic map of 10 geomorphological classes was produced for Torres Strait with an overall accuracy of 75%. The OBIA approach employed in this research has enabled the geomorphology of reef platforms to be mapped for the first time at such accuracy and descriptive resolution.

Keywords:

• OBIA
• Torres Strait
• neural networks
• classification
• Landsat ETM+

Acknowledgements

This research represents a component of doctoral research undertaken by JL during tenure of University of Wollongong IPRS scholarship. We wish to thank Scott Smithers and Kevin Parnell from James Cook University for support particularly during fieldwork, the island councils on those islands visited in Torres Strait for access to field sites, Tom Taranto and Tim Skewes from CSIRO for reef monitoring datasets, Laurie Chisholm from University of Wollongong for the provision of Definiens Developer software, and Prashanth Marpu for helpful comments on OBIA.