Publication Date:
2024-04-20
Description:
A subset of photoquadrats were uploaded to the CoralNet machine learning interface (https://coralnet.ucsd.edu/) and manually labelled for coral, algae or substrate type using 50 points per quadrat. Follow training of the machine, this training set enabled automatic annotation of all unclassified field images: the remaining field photos were uploaded to the database and 50 annotation points were overlaid on each of the images. Every point 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 WGS-84.
Keywords:
Acanthaster planci, cover; Acropora, cover; Acropora formosa, cover; Acroporidae, cover; Alcyoniidae, cover; Algae, cover; Background, cover; Benthic microalgae, cover; Caulerpa sp., cover; Chlorodesmis sp., cover; Coral cover, branching corals; Coralline algae, cover; Corals indeterminata, cover; Cyanobacteria, cover; DATE/TIME; Dictyota sp., cover; Epithelial algal matrix, cover; Favia, cover; GBR_MAP; GBR habitat mapping; Gorgonia, cover; Great Barrier Reef, Australia; Halimeda sp., cover; Identification; Image; Image number/name; Invertebrata, cover; LATITUDE; Lobophora, cover; LONGITUDE; Montipora, cover; Other, cover; Padina sp., cover; Pocilloporidae, cover; Porites cylindrica, cover; Porites lichen, cover; Porites lobata, cover; Sand, cover; Sargassum sp., cover; Seagrass, cover; Soft corals, other, cover; Townsville-Whitsunday; Turbinaria sp., cover
Type:
Dataset
Format:
text/tab-separated-values, 1318604 data points
Permalink