Mission-specific AI and machine learning capabilities for combat aircraft have been delivered to the Multi-Domain Mission Support System (MD MSS) for the first time, marking a significant milestone for UK Defense AI. Built through close collaboration between Thales, RAF Digital and NAD (National Armaments Director Group), the product is also the first operational deployment of AI from the Thales UK cortAIx factory.
The measure of AI in defense is not something that can be achieved in a laboratory. That’s what we can achieve in service.
A system built for today’s complex operations
MD MSS has been in continuous operation since 1986. What began as a mission data system for the Nimrod maritime patrol aircraft has evolved over 40 years of spiral development with the UK Ministry of Defense into the Royal Air Force’s primary system for multi-domain mission support.
The current contract, signed by DE&S (now NAD) in 2021 and extended through 2026, maintains and develops systems used on a wide range of platforms, including the F-35B Lightning II, Typhoon, Poseidon, Voyager and Chinook. MD MSS is also installed on board HMS Queen Elizabeth and HMS Prince of Wales, supporting air operations by carrier strike groups.
At its core, the MD MSS processes, transmits, and manipulates complex mission data from multiple sources and locations, quickly providing critical information to the crew and planners on the ground. It provides the situational awareness and communications interoperability required for modern multi-domain operations, supporting effective and rapid decision-making at both operational and tactical levels. The latest program milestones build on this foundation.
Incremental changes rather than updates
MD MSS has long included analytical tools such as lifestyle pattern visualization and behavioral alerts to help operators manage the amount of data flowing through the system. These features have been battle-tested through years of operational service, but they are rules-based. That is, it responded to predefined parameters rather than learning from the data itself.
Those currently in operation are of a different dimension. Thales has introduced the first true machine learning capabilities within MD MSS using Thales cortAIx Factory’s parsimonious learning methodology developed in collaboration with Faculty AI.
The system trains on limited operational data to build adaptive models of normal and abnormal behavior. It will initially be applied to maritime track analysis to monitor shipping patterns, filter routine activity, and identify anomalies that cannot be recognized within the large amount of data available to operators. The key is to do this using the limited real-world operational data that is actually available, rather than the large, curated datasets that many other AI systems rely on.
From concept to function
This feature did not emerge from an independent research program. Instead, it was born out of a deliberate effort by Thales UK’s cortAIx Lab to explore how machine learning can be applied across defense use cases to deliver real operational benefits from limited operational data. The effort, called AI DAMS (AI for Decision Advantage and Mission Support), was developed and tested in collaboration with Faculty AI through early prototypes to prove the concept. Thales then approached RAF Digital and DE&S to work together to build a more mature demonstrator using MD MSS’s existing secure application hosting and data fabric capabilities.
“MD The integration of AI into the MSS represents a further step forward in this enhancement of the Royal Air Force’s operational capabilities.The ability to rapidly examine and interpret complex mission data directly supports more timely and informed decision-making in demanding environments. From a materiel perspective, this milestone demonstrates how cutting-edge digital technology can be quickly and effectively integrated into proven and operational systems, reinforcing the value of sustained collaboration between the Ministry of Defence, RAF Digital and industry partners.”
Alex Buckley – Team Leader NAD Materials
“This is a significant step forward for the use of AI in the Royal Air Force’s operational systems. By enabling operators to analyze complex mission data faster and focus on what matters most, this capability supports faster and more informed decision-making. This is also a significant milestone for MD MSS, demonstrating how we can integrate AI into our proven operational capabilities in a practical and mission-relevant way.”
Terry Makewell – RAF Chief Digital & Technology Officer
Framework for the future
Although maritime route analysis is the first application of parsimony learning within MD MSS, it establishes the foundation for further development across additional route types and domains. The AI framework currently built into the system can support expansion to flight trajectories and other data sources as the program evolves.
This development has broader significance beyond MD MSS. It is the first operational delivery of mission-focused AI from the group’s dedicated AI accelerator, the Thales UK cortAIx factory. cortAIx has extensive influence within Thales around the world, but this marks the first time its capabilities have been offered to the UK military services. We have also established a repeatable collaborative model for moving AI from research to operational deployment, opening the door to further AI capability development across the UK Armed Forces.
Photo courtesy of Thales
