Research Project
Full description Field photos were uploaded to the CoralNet machine learning interface (https://coralnet.ucsd.edu/). A presviously trained subset of photoquadrats were uploaded as training images. Fifty annotation points were overlaid on all Great Barrier Reef (GBR) Legacy images and each was assigned a benthic cover category from a label list automatically by the program. The resulting benthic cover data of each photo was linked to gps coordinates, saved as an ArcMap point shapefile, and projected to Universal Transverse Mercator WGS84 Zone 55 South.