This post is also available in: heעברית (Hebrew)

RF signals can provide valuable insight into commercial vessel activity across the globe, even when bad actors seek to hide their location. New maritime security and vessel monitoring capabilities developed by HawkEye 360, specializing in radio frequency (RF) geospatial intelligence, provide a response to that challenge.

The technology combines the company’s powerful RF geolocation services with a customized machine learning model developed through Amazon Web Services’ (AWS) Machine Learning (ML) Solutions Lab. 

The RF signals analysis and machine learning ability can help make the oceans a safe place by supporting a variety of applications, including commercial maritime activity, national security operations, maritime domain awareness, environmental protection and more.

The capabilities leverage underlying vessel characteristics and behavior to predict whether a given vessel is likely to engage in similar activity as sanctioned vessels.

The company used Amazon SageMaker Autopilot — a fully managed service that helps make it easy to build, train and deploy ML models quickly — to develop the purpose-built, proprietary algorithms undergirding the new capabilities. These algorithms can help 

generate deeper insights into RF data in half the time than was previously possible.

“With these machine learning-backed capabilities, we will empower customers to cut through an ocean full of noise to obtain more timely and critical insights from maritime RF data to improve mission outcomes and prevent illegal and illicit activities,” according to the company’s announcement.

The new algorithms evaluate vessels’ historical data and known interactions, along with contextual vessel characteristics to generate insights into the complex connections involved in illicit maritime vessel activity, such as illegal fishing, human trafficking, ship-to-ship transfer of illegal goods, smuggling and more. This provides analysts with a holistic view of maritime activity and the ability to detect, predict and zoom in on high-risk activity.