A global coral reef probability map generated using convolutional neural networks

Li, Jiwei, Knapp, David E., Fabina, Nicholas S., Kennedy, Emma V., Larsen, Kirk, Lyons, Mitchell B., Murray, Nicholas J., Phinn, Stuart R., Roelfsema, Chris M., and Asner, Gregory P. (2020) A global coral reef probability map generated using convolutional neural networks. Coral Reefs, 39 (6). pp. 1805-1815.

[img] PDF (Published Version) - Published Version
Restricted to Repository staff only

View at Publisher Website: https://doi.org/10.1007/s00338-020-02005...
 
1
4


Abstract

Coral reef research and management efforts can be improved when supported by reef maps providing local-scale details across global extents. However, such maps are difficult to generate due to the broad geographic range of coral reefs, the complexities of relating satellite imagery to geomorphic or ecological realities, and other challenges. However, reef extent maps are one of the most commonly used and most valuable data products from the perspective of reef scientists and managers. Here, we used convolutional neural networks to generate a globally consistent coral reef probability map-a probabilistic estimate of the geospatial extent of reef ecosystems-to facilitate scientific, conservation, and management efforts. We combined a global mosaic of high spatial resolution Planet Dove satellite imagery with regional Millennium Coral Reef Mapping Project reef extents to build training, validation, and application datasets. These datasets trained our reef extent prediction model, a neural network with a dense-unet architecture followed by a random forest classifier, which was used to produce a global coral reef probability map. Based on this probability map, we generated a global coral reef extent map from a 60% threshold of reef probability (reef: probability >= 60%, non-reef: probability < 60%). Our findings provide a proof-of-concept method for global reef extent estimates using a consistent and readily updateable methodology that leverages modern deep learning approaches to support downstream users. These maps are openly-available through the Allen Coral Atlas.

Item ID: 64719
Item Type: Article (Research - C1)
ISSN: 1432-0975
Keywords: Coral reef, Deep learning, Earth observation, Planet Dove, Millennium Coral Reef Mapping Project, Remote sensing
Copyright Information: © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Funders: Arizona State University (ASU), National Geographic (NG), Planet Inc. (PI), University of Queensland (UQ)
Date Deposited: 21 Oct 2020 08:18
FoR Codes: 05 ENVIRONMENTAL SCIENCES > 0501 Ecological Applications > 050104 Landscape Ecology @ 20%
01 MATHEMATICAL SCIENCES > 0199 Other Mathematical Sciences > 019999 Mathematical Sciences not elsewhere classified @ 50%
08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080106 Image Processing @ 30%
SEO Codes: 96 ENVIRONMENT > 9605 Ecosystem Assessment and Management > 960501 Ecosystem Assessment and Management at Regional or Larger Scales @ 100%
Downloads: Total: 4
More Statistics

Actions (Repository Staff Only)

Item Control Page Item Control Page