U.S. forges maritime technology collaborations to improve domain awareness

To safeguard maritime borders, the United States military is promoting cooperative technology efforts to provide near-real time global maritime situational awareness to combat everything from illegal fishing and human trafficking to sovereignty threats.

Recent successes include the U.S. Naval Research Laboratory’s (NRL’s) new program, called Proteus, to identify, query and filter maritime vessels based on user-defined criteria and the Defense Innovation Unit’s (DIU’s) international competition, known as xView3, to create machine learning models to locate and distinguish maritime vessels with synthetic aperture radar.

The U.S. Navy and U.S. Coast Guard, in particular, are also pushing for broader collaborations among allies and partners to apply advanced military technologies, including surveillance satellites, high-resolution radar and data-sharing software, to maritime security challenges, experts said.

Advanced maritime capabilities are in high demand as security threats such as illegal, unreported and unregulated (IUU) fishing continue to worsen worldwide and contribute to broader stability issues.

The People’s Republic of China is “obviously high on the list … when talking about state-sponsored IUU and the way that they use it as both a tool for … economic purposes, but also increasingly for the purposes of influencing bilateral relationships,” Whitley Saumweber, director of the Center for Strategic and International Studies’ Stephenson Ocean Security Project, said in December 2021, according to National Defense magazine.

“IUU fishing is one of the leading global maritime security threats whose impacts are pervasive and far-reaching, threatening the economic and food security of all nations, particularly developing coastal states,” Rear Adm. Scott Clendenin, U.S. Coast Guard assistant commandant for response policy, said in a January 2022 DIU news release.

“The vastness of the ocean requires that we leverage extensive data analysis to detect and characterize vessels operating without” automatic identification systems or vessel monitoring systems, Clendenin said.

“Artificial intelligence combined with satellite imagery provides a new capability to detect suspected IUU fishing vessels that may otherwise elude U.S. and partner nations fisheries enforcement agencies. This increased maritime domain awareness can be shared with like-minded partner nations to enable them to protect their sovereignty.”

The NRL’s Proteus software, pictured, monitors sea vessels so stakeholders can “collaboratively discover and investigate suspicious and illegal maritime activity throughout the world in ways never before possible,” said Cameron Naron, the U.S. Maritime Administration’s maritime security director.

Proteus automatically produces worldwide vessel tracks via an integrated system of maritime domain awareness capabilities that processes and fuses data from many sources. The system features a data collector and aggregator, a multi-source data fusion engine, a complex event processor, a maritime domain awareness services layer, a web-based common operating picture and analytic tools, NRL said.

Meanwhile, DIU held the xView3 contest in late 2021 to develop an open-source computer vision algorithm to detect so-called dark vessels — which don’t broadcast their location — engaged in illegal fishing and determine their size and speed. More than 1,900 participants from 67 countries submitted candidate algorithms that create 2D and 3D reconstructions of data from synthetic aperture radar.

DIU announced five winners from five countries January 31, 2022, who will split the U.S. $150,000 prize. DIU partnered with the international nonprofit Global Fishing Watch (GFW), the U.S. Coast Guard, the U.S. National Oceanic and Atmospheric Administration, and the U.S. National Maritime Intelligence-Integration Office.

“Digital tools that come from efforts like the xView3 competition are vital to increasing our knowledge of human activity on the water and helping our global partners have targeted, effective, intelligence-driven operations,” said Paul Woods, GFW co-founder and chief innovation officer.

“The machine learning models developed as part of this challenge will help our U.S. and international partners identify potential IUU fishing activity at a speed and scale that would be practically impossible for human analysts alone,” said Jared Dunnmon, DIU’s technical director for artificial intelligence and machine learning. “Instead of asking human beings to look through specific satellite images we think may be important — which may take several hours per image — we can use modern computer vision algorithms to look through every single satellite image we record in a matter of minutes.”

Winning algorithms from the xView3 contest will be integrated into the U.S. Navy’s SeaVision maritime domain awareness and Proteus systems.

To learn more about Proteus, email Proteus-info@spacemail.nrl.navy.mil.

IMAGE CREDIT: U.S. NAVAL RESEARCH LABORATORY