The use of artificial intelligence/machine learning (AI/ML) is critical to efforts to modernize U.S. Northern Command and North American Aerospace Defense Command (NORAD), including the North Warning System (NWS), U.S. Air Force General Glen VanHerck, the NORTHCOM and NORAD commander said on July 28.

If a threat parameter threshhold is met through AI/ML analysis of data from one sensor, another sensor, for example a space-based geospatial intelligence satellite, could cross cue to provide a closer look and provide significant early warning.

“What we’ve seen is the ability to get way further what I call left, left of being reactive to actually being proactive, and I’m not talking not minutes and hours. I’m talking days,” VanHerck said during a Pentagon briefing to discuss DoD’s Global Information Dominance Experiments (GIDE). The 11 combatant commands recently held the third GIDE experiment.

“The ability to see days in advance creates decision space–decision space for me as an operational commander to potentially posture forces to create deterrence options to provide that to the secretary or even the president, too use messaging, the information space to create deterrence options and messaging and if required to get further ahead and posture ourselves for defeat [of adversaries],” VanHerck said.

The Air Force spends about $6 billion annually on systems for Arctic security and operations, and the service will likely step up its investment, including the modernization of NWS (Defense Daily, July 27).

NORAD modernization has been a topic of conversation among President Biden and Canadian Prime Minister Justin Trudeau.

A successor to the 1950s Distant Early Warning (DEW) line, NWS, first fielded in the late 1980s, consists of 25 Lockheed Martin [LMT] AN/FPS-117 long-range radars and 36 short-range AN/FPS-124 radars. NWS provides early warning of possible incursions into U.S. airspace and covers nearly 3,000 miles across North America from the Aleutian Islands in southwestern Alaska to Baffin Island in northeastern Canada.

The Air Force wants improved sensors and communications for the Arctic, including Joint All Domain Command and Control, as the service seeks to make operations there more routine, as the service seeks better awareness of potential adversary activities there, and as the service fields Lockheed Martin F-35s to enhance U.S. Arctic power projection to the Pacific, Europe, and the Middle East.

Air Force Lt. Gen. David Krumm, the commander of Alaskan Command and the 11th Air Force, has suggested that radar modernization for the Arctic is vital, as the legacy radars “were designed primarily to detect Soviet bombers coming to attack over the poles,” not the hypersonic weapons and cruise missiles on the current U.S. watchlist.

A NORTHCOM/NORAD Pathfinder initiative “is processing more sensor data than the current command and control system used for air defense of North America,” according to Hardening the Shield: A Credible Deterrent & Capable Defense for North America, a paper last September by retired Air Force Gen. Terrence O’Shaughnessy–the former NORAD commander–and Air Force Maj. Gen. Peter Fesler, NORAD’s deputy director of operations.

Pathfinder also “is identifying information buried in the data, giving new life to old sensors” and has been able to identify and track very small drones “previously thought to beyond the capability of the system,” per the paper.

On July 28, VanHerck said that NORAD has applied Pathfinder to analyze the raw data from the NWS radar sensors.

“What we found is about 98 percent of the data and information was not being actually analyzed or assessed under the prior way we conducted operations,” VanHerck said. “Now by taking the raw data and applying Pathfinder, which uses machine learning and artificial intelligence, we’re actually able to assess 100 percent of the data. And that gives us a much better capability.

VanHerck said that “any sensor capability that NORAD modernization provides such as over-the-horizon radar technology — a polar over-the-horizon radar would be able to fit right into this as long as you make the data and information available to share.”