PREDICTING THE NEXT PORT VISIT OF A VESSEL USING AIS DATA
Loading...
Authors
Pham, Cang K.
Subjects
Automatic Identification System
AIS
supervised learning
random forests
navigation
prediction
Baltic Sea
AIS
supervised learning
random forests
navigation
prediction
Baltic Sea
Advisors
Koyak, Robert A.
Date of Issue
2019-12
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
This thesis develops a procedure to estimate the probability distribution of the next destination a ship will visit after it departs a specific port using historical Automatic Identification System (AIS) data in the Baltic Sea region. AIS was developed to facilitate communication between vessels in a region by broadcasting information, such as vessel name, position, heading, and speed, on regular time intervals. We develop a data-driven procedure to locate the stopping point of a vessel along shorelines, and we construct vessel itineraries using historical AIS data to form a supervised learning data set. A machine-learning approach is used to update the probability that the ship will visit a port as it is underway. This research enhances understanding of patterns of navigation in a particular region, which is useful for tracking, monitoring, and detecting anomalous behavior at sea.
Type
Thesis
Description
Series/Report No
Department
Operations Research (OR)
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Approved for public release; distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.