Maritime Domain Awareness (MDA), as defined in the 2005 National Strategy for Maritime Security, is the effective understanding of anything associated with the global maritime domain that could impact the security, safety, economy, or environment of the United States. Thus, it is imperative for the U.S. Navy to develop approaches that enhance understanding of the maritime domain in order to maintain operational effectiveness. One such way to enhance this understanding is to develop approaches that automate the analysis of Automatic Identification System (AIS) data to characterize the behavior of ships in the maritime domain. By the sheer amount of AIS data available, it quickly becomes challenging for a human operator to identify ship behaviors throughout the world. When timeliness is important for decision makers, it becomes even more important that the characterization of ship behavior is done quickly and accurately to identify potential issues or threats. Thus, a major contribution of this thesis is the development of an autonomous machine learning system that characterizes ship behavior quickly and accurately in order to achieve MDA in a particular environment. This includes an autonomous system for the identification of ship tracks in a region. Two major contributions of this work are the development of a taxonomy of ship behaviors, which is currently lacking in the literature, and a report on the characterization of such behaviors through machine learning methods.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Maritime Domain Awareness: C4I for the 1000 Ship Navy

    M. Agnello / J. Astudillo / J. Brown et al. | NTIS | 2009



    Basin-Wide Maritime Awareness From Multi-Source Ship Reporting Data

    Harm Greidanus / Marlene Alvarez / Torkild Eriksen et al. | DOAJ | 2013

    Free access

    Advanced Ship Detection for Spaceborne Based Maritime Awareness

    Radius, A. / Ferreira, J. / Carmo, P. et al. | British Library Conference Proceedings | 2013