Detecting suspicious activities at sea based on anomalies in Automatic Identification Systems transmissions

Area of Science:

• Maritime Safety
• Remote Sensing
• Statistical Modeling

Background:

• Automatic Identification Systems (AIS) are vital for maritime navigation and collision avoidance.
• Remote vessel monitoring using AIS data is increasingly common, especially with satellite receivers.
• Gaps in AIS transmissions pose a challenge, stemming from system saturation, equipment issues, or intentional disabling.

Purpose of the Study:

• To develop and validate a spatial statistical model for identifying the causes of AIS transmission gaps.
• To differentiate between unintentional AIS gaps (saturation, equipment failure) and intentional transmitter disabling.
• To assess the model's effectiveness in identifying high-risk gaps indicative of illicit activities.

Main Methods:

• Development of a spatial statistical model to analyze AIS transmission gaps.
• Calculation of the probability of intentional disabling for identified AIS gaps.
• Application and testing of the model in a case study within the Arafura Sea.

Main Results:

• The developed model successfully identified high-risk gaps in the Arafura Sea case study.
• Simulations demonstrated the model's sensitivity to frequent gaps as short as one hour.
• Vessels identified as high-risk for intentional AIS disabling were accurately ranked by the model.

Conclusions:

• The spatial statistical model is effective in identifying intentional AIS disabling.
• Accurate identification of intentional disabling can enhance enforcement against illegal fishing and other illicit maritime activities.
• This approach offers improved opportunities for maritime security and regulatory enforcement.