Details:

• Journal Title:
  OCEANS 2023 - MTS/IEEE
• Personal Author:
  Cromwell, M. ; Mesick, S. ; Malik, M. ; Gondle, V.

  Cromwell, M. ; Mesick, S. ; Malik, M. ; Gondle, V. Less -
• NOAA Program & Office:
  Ocean Exploration Program ; OAR (Oceanic and Atmospheric Research) ; NOS (National Ocean Service) ; NESDIS (National Environmental Satellite, Data, and Information Service) ; NCEI (National Centers for Environmental Information)

  Ocean Exploration Program ; OAR (Oceanic and Atmospheric Research) ; NOS (National Ocean Service) ; NESDIS (National Environmental Satellite, Data, and Information Service) ; NCEI (National Centers for Environmental Information) Less -
• Description:
  Underwater imagery (including video and still frame photos) are routinely collected with crewed and uncrewed submersible platforms and represent an unparalleled visual repository of knowledge about marine organisms and how they interact with their environment in a given spatiotemporal setting. Underwater images are of key importance for scientific analysis to inform policy and resource management decisions and are also in high demand for media and documentary releases. Underwater imagery requires accompanying metadata describing the contents of the imagery to achieve FAIR (Findable, Accessible, Interoperable, and Reusable) guidelines. This essential metadata generation step is an intense - often manual - process requiring scientists to provide video annotations that are a prerequisite to achieving Open Science initiatives and ensuring that data are available for broad exploitation in standard or common formats. Unique data management challenges set underwater imagery apart from most other oceanographic and geophysical data collections. Consistently high data volumes coupled with rapidly evolving technical advances in sensors can exceed data processing, management, and user capabilities. These challenges often require unique storage and data access solutions. These concerns are compounded by imagery collected from previous sea-going expeditions. These historical data - often decades old - take on a new importance in the face of climate change, and represent an opportunity to evaluate - visually and quantitatively - change over time for a specific organism or location. It is necessary that these historically significant records are retained and equally available for comparative analysis. Through the past two decades, the National Oceanic and Atmospheric Administration has researched, implemented, and refined processes that support best data management practices at minimal cost.
• Keywords:
  [+]

  Artificial Intelligence Deep Learning (Machine Learning) Information Technology Machine Learning Open Scholarship AI Data Management Digital Archives FAIR (findable, Accessible, Interoperable, Reusable) Ocean Imagery Open Science Underwater Imagery Video Data
• Source:
  OCEANS 2023 - MTS/IEEE U.S. Gulf Coast, Biloxi, MS, USA, 2023, pp. 1-7
• DOI:
  https://doi.org/10.23919/OCEANS52994.2023.10337329
• Format:
  PDF
• Document Type:
  Journal Article
• Rights Information:
  Accepted Manuscript
• Rights Statement:
  The NOAA IR provides access to this content under the authority of the government's retained license to distribute publications and data resulting from federal funding. While users may legally access this content, the copyright owners retain rights that govern the reproduction, redistribution, and re-use of this work. The user is solely responsible for complying with applicable copyright law.
• Compliance:
  Submitted
• Main Document Checksum:
  [+]

  urn:sha-512:5fd001254da9ae8b58f7cd6a3caf373e147575b5d4ed466446c3cf4fee903f35d6ab23fb4a5704ffbe558baa144b8d253d62799e575f637c713c2645e28a2c80
• Download URL:
  https://repository.library.noaa.gov/view/noaa/61084/noaa_61084_DS1.pdf
• File Type:
  [PDF-448.39 KB]