How AI can protect vital pipelines and cables deep in the ocean

Huge stretches of these critical connectors lie unprotected in the murky depths—and vulnerable to attacks such as the 2022 sabotage of the Nord Stream pipelines that carry Russian natural gas to Europe under the Baltic Sea.

Now, in the way that the use of drones has changed the conduct of land wars, artificial intelligence is about to change everything about how the deep sea is navigated and how critical underwater infrastructure is protected in wartime and against threats of terrorism.

It’s hard to get a look at this undersea world in order to protect it. Data is fragmented and comes from systems ranging from sonar to satellites. Analyzing it often takes weeks. What’s needed is a sort of Google Maps of the sea that not only accurately replicates the oceans and their terrain but also provides timely alerts on potential threats. That’s where AI’s ability to sift through vast amounts of data comes in.

AI-empowered underwater systems are already changing seabed warfare and defense. Drones and anti-mine robots, working together with ships on the surface, underwater sensors and satellites, are being deployed by the military and governments. These systems to navigate, map, and provide underwater defense are increasingly using AI to analyze and synthesize diverse sources of data.

In the next few years, industry and military users expect these systems to make huge advances.

Armed with a map of the objects in the ocean and high-resolution data, autonomous systems will identify the things that don’t belong, says Jann Wendt, chief executive of German startup North.io, which is working to create systems to protect undersea technology. Determining whether an object encroaching on a group of offshore wind turbines is a threat or just a pod of dolphins, or whether an object near a critical undersea cable is a rock or a mine, is crucial, he says. Wind turbines are vulnerable because they are buried in the seabed and are connected to the power grid on land with undersea cables.

The ultimate goal is to make the sea essentially transparent as technology monitors thousands of miles of cable and other installations in real time.

After the Nord Stream incident, the North Atlantic Treaty Organization created a team to find ways to protect underwater infrastructure in the territories of the alliance. Responding to suspected attacks by Russian-linked ships on underwater cables, NATO in January launched the Baltic Sentry operation, which includes a small fleet of underwater drones. Russia has denied any wrongdoing.

AI is central to NATO’s effort, says Lt. Col. Rene Heise, a staff officer in this group, known as the Critical Undersea Infrastructure Coordination Cell. “In the future, unmanned maritime systems in the air and underwater are going to be active," he says. “AI will help us develop the systems that will enable us to identify and combat suspicious behavior underwater."

Based in the northern German city of Kiel, North.io is working with technology from U.S. tech giants including Nvidia and International Business Machines. The German government is financing a North.io project called Argus, aimed at analyzing data to detect threats, at a total cost of 3.5 million euros, equivalent to $3.7 million.

North.io, which has about 70 employees, acts as a kind of warehouse that collects data from a wide variety of sources and trains its AI to make sense of it, to show what is happening in the ocean at any time—hoping eventually to do so in real time.

At great depths in the ocean there is little light, so the data needed for navigation or observation is mainly acoustic. The information—collected by academic research institutes, wind-farm operators and other sea-based commercial operations—comes from sonar systems that locate objects in the ocean, seismic recording devices that register earthquakes, and satellites.

North.io’s innovation has been to create a way to manage the huge amount of data and standardize it to make it accessible on a variety of cloud-based systems. Its main product is the TrueOcean data-management system, with users that include the military, research institutes and companies in the offshore wind industry.

“We are creating a digital twin of the ocean," Wendt says. “This wasn’t possible a few years ago."

The growing capabilities of AI are also fueling a trend toward unmanned defense systems in the military. Underwater drones were originally developed to scan the ocean and collect data for industry and research. But over the past few years, navies and governments have increasingly begun using these autonomous underwater vehicles, or AUVs, to enhance defense. Many of the big defense competitors in the U.S. and elsewhere are building underwater drones, including BAE Systems, Northrop Grumman, Boeing and upstart Anduril.

The U.S. Navy and the Pentagon’s Defense Innovation Unit—created in 2015 to accelerate the military’s adoption of cutting-edge technology that is commercially available—in January purchased an autonomous underwater vehicle called Hugin from the Norwegian manufacturer Kongsberg Discovery. It will be tested by the Navy’s advanced undersea warfare unit, says Daniel Redmon, a DIU official involved in acquiring the vehicle.

Kongsberg developed Hugin for dual civilian and military use, says Rich Patterson, U.S.-based vice president of sales for Kongsberg’s unmanned systems. The AUV, which looks like a mini submarine and plumbs depths of as much as 6,000 meters (3.7 miles), can carry an array of advanced sonar sensors—including a type of sonar that can map beneath the seabed—as well as cameras, lasers and more.

Still, a number of obstacles remain for creating the kind of precise, real-time map of the ocean and objects that would be required for complete undersea autonomy. For instance, today’s underwater vehicles used to clear mines typically can identify only objects they already know. So if the threatening object isn’t in the AI’s catalog, it might not be recognized as a threat.

“It’s going to require a lot more undersea infrastructure being built," says Redmon of the DIU. “We’re going to require things like charging stations, spots where we can offload data, and we’ve only mapped around 10% of the ocean at this point."

Write to future@wsj.com