BCO-DMO BlogDataset: Manually annotated reef halos from 6 study areas
Data Citation:
Madin, E., Franceschini, S. (2024) Manually annotated reef halos based on sattelite imagery from 6 study areas as training and test data for a deep learning model. Biological and Chemical Oceanography Data Management Office (BCO-DMO). (Version 1) Version Date 2024-12-18 [if applicable, indicate subset used]. doi:10.26008/1912/bco-dmo.932211.1 [access date]
Terms of Use
This dataset is licensed under Creative Commons Attribution 4.0.
If you wish to use this dataset, it is highly recommended that you contact the original principal investigators (PI). Should the relevant PI be unavailable, please contact BCO-DMO (info@bco-dmo.org) for additional guidance. For general guidance please see the BCO-DMO Terms of Use document.
DOI:10.26008/1912/bco-dmo.932211.1
Spatial Extent: N:27.74960245 E:151.9375651 S:-23.47546301 W:-87.87905306
Principal Investigator:
Elizabeth Madin (University of Hawaiʻi at Mānoa, HIMB)
Scientist:
Simone Franceschini (University of Hawaiʻi at Mānoa, HIMB)
Contact:
Elizabeth Madin (University of Hawaiʻi at Mānoa, HIMB)
BCO-DMO Data Manager:
Karen Soenen (Woods Hole Oceanographic Institution, WHOI BCO-DMO)
Version:
1
Version Date:
2024-12-18
Restricted:
No
Validated:
Yes
Current State:
Final no updates expected
Manually annotated reef halos based on sattelite imagery from 6 study areas as training and test data for a deep learning model
Abstract:
Reef halos are rings of bare sand that surround coral reef patches. Halo formation is likely to be the indirectly result of interactions between relatively healthy predator and herbivore populations. To reduce the risk of predation, herbivores preferentially graze close to the safety of the reef, potentially affecting the presence and size of the halo. Reef halos are readily visible in remotely sensed imagery, and monitoring their presence and changes in size may therefore offer clues as to how predator and herbivore populations are faring. However, manually identifying and measuring halos is slow and limits the spatial and temporal scope of studies. There are currently no existing tools to automatically identify single reef halos and measure their size to speed up their identification and improve our ability to quantify their variability over space and time.
Here we present a set of convolutional neural networks aimed at identifying and measuring reef halos from very high-resolution satellite imagery (i.e., ∼0.6 m spatial resolution). We show that deep learning algorithms can successfully detect and measure reef halos with a high degree of accuracy (F1 = 0.824), thereby enabling faster, more accurate spatio-temporal monitoring of halo size. This tool will aid in the global study of reef halos, and potentially coral reef ecosystem monitoring, by facilitating our discovery of the ecological dynamics underlying reef halo presence and variability.
©2024 Biological and Chemical Oceanography Data Management Office.
