CoralNet offers a new way to analyze data essential to the conservation of coral reefs experiencing catastrophic declines in biodiversity worldwide. Traditionally, coral reef research entails meticulous surveys, which generates large datasets that need to be annotated and analyzed by hand, creating a data analytics bottleneck. To address this problem, CoralNet utilizes a type of machine learning called annotation (which is the process of automatically fully or partially assigning metadata) to tag images of coral reefs with keywords and/or captioning, allowing data to be processed much faster. CoralNet is also more than a mechanism to analyze data. It has evolved to become a network: a data depository and collaborative tool for researchers and coral enthusiasts with a passion for coral data. CoralNet received funding from the National Science Foundation and NOAA, and in 2019, a study published by researchers at NOAA in Frontiers in Marine Science confirmed that CoralNet was as accurate as a human in annotating images. CoralNet will continue to develop and provide the tools to better monitor coral reefs and their rich biodiversity. 


CoralNet. (2020). “About CoralNet.”

Williams, Ivor Douglas, Courtney Couch, Oscar Beijbom, Thomas Oliver, Bernardo Vargas-Angel, Brett Schumacher, and Russell Brainard. “Leveraging automated image analysis tools to transform our capacity to assess status and trends on coral reefs.” Frontiers in Marine Science 6 (2019): 222

Lozada-Misa, Paula, Brett Schumacher, and Bernardo Vargas-Ángel. “Analysis of benthic survey images via CoralNet: a summary of standard operating procedures and guidelines.” (2017).


See also:


CoralNet. (2020). “About CoralNet.”


Artificial Intelligence, Biodiversity, Citizen Science, Data, Ecological Monitoring