Artificial intelligence for right whale photo identification : from data science competition to worldwide collaboration

dc.contributor.authorKhan, Christin
dc.contributor.authorBlount, Drew
dc.contributor.authorParham, Jason
dc.contributor.authorHolmberg, Jason
dc.contributor.authorHamilton, Philip
dc.contributor.authorCharlton, Claire
dc.contributor.authorChristiansen, Fredrik
dc.contributor.authorJohnston, David
dc.contributor.authorRayment, Will
dc.contributor.authorDawson, Steve
dc.contributor.authorVermeulen, Els
dc.contributor.authorRowntree, Victoria
dc.contributor.authorGroch, Karina
dc.contributor.authorLevenson, J. Jacob
dc.contributor.authorBogucki, Robert
dc.date.accessioned2023-07-19T09:44:24Z
dc.date.available2023-07-19T09:44:24Z
dc.date.issued2022-06
dc.description.abstractPhoto identification is an important tool in the conservation management of endangered species, and recent developments in artificial intelligence are revolutionizing existing workflows to identify individual animals. In 2015, the National Oceanic and Atmospheric Administration hosted a Kaggle data science competition to automate the identification of endangered North Atlantic right whales (Eubalaena glacialis). The winning algorithms developed by Deepsense.ai were able to identify individuals with 87% accuracy using a series of convolutional neural networks to identify the region of interest, create standardized photographs of uniform size and orientation, and then identify the correct individual. Since that time, we have brought in many more collaborators as we moved from prototype to production. Leveraging the existing infrastructure by Wild Me, the developers of Flukebook, we have created a web-based platform that allows biologists with no machine learning expertise to utilize semi-automated photo identification of right whales. New models were generated on an updated dataset using the winning Deepsense.ai algorithms. Given the morphological similarity between the North Atlantic right whale and closely related southern right whale (Eubalaena australis), we expanded the system to incorporate the largest long-term photo identification catalogs around the world including the United States, Canada, Australia, South Africa, Argentina, Brazil, and New Zealand. The system is now fully operational with multi-feature matching for both North Atlantic right whales and southern right whales from aerial photos of their heads (Deepsense), lateral photos of their heads (Pose Invariant Embeddings), flukes (CurvRank v2), and peduncle scarring (HotSpotter). We hope to encourage researchers to embrace both broad data collaborations and artificial intelligence to increase our understanding of wild populations and aid conservation efforts.en_US
dc.description.departmentMammal Research Instituteen_US
dc.description.librarianhj2023en_US
dc.description.sponsorshipNOAA Fisheries High Performance Computing IT Incubator, NOAA Fisheries NERAP/EBFM and the Bureau of Ocean Energy Management. Each of the photo-identification catalogs were supported by multiple funding sources over the many decades of their curation.en_US
dc.description.urihttps://link.springer.com/journal/42991en_US
dc.identifier.citationKhan, C., Blount, D., Parham, J. et al. Artificial intelligence for right whale photo identification: from data science competition to worldwide collaboration. Mammalian Biology 102, 1025–1042 (2022). https://doi.org/10.1007/s42991-022-00253-3.en_US
dc.identifier.issn1616-5047 (print)
dc.identifier.issn1618-1476 (online)
dc.identifier.other10.1007/s42991-022-00253-3
dc.identifier.urihttp://hdl.handle.net/2263/91533
dc.language.isoenen_US
dc.publisherSpringeren_US
dc.rights© The Author(s) 2022. Open Access. This article is licensed under a Creative Commons Attribution 4.0 International License.en_US
dc.subjectAutomated matchingen_US
dc.subjectAutomated pattern recognitionen_US
dc.subjectComputer visionen_US
dc.subjectIndividual identificationen_US
dc.subjectMachine learningen_US
dc.subjectRight whaleen_US
dc.subjectSDG-14: Life below wateren_US
dc.subjectNorth Atlantic right whale (Eubalaena glacialis)en_US
dc.subjectSouthern right whale (Eubalaena australis)en_US
dc.titleArtificial intelligence for right whale photo identification : from data science competition to worldwide collaborationen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
Khan_Artificial_2022.pdf
Size:
2.02 MB
Format:
Adobe Portable Document Format
Description:
Article
Loading...
Thumbnail Image
Name:
Khan_ArtificialSuppl1_2022.pdf
Size:
195.83 KB
Format:
Adobe Portable Document Format
Description:
Supplementary Material 1

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: