China tests AI radar that defeats electronic warfare jamming with 99% tracking accuracy

September 8, 2025

China has reportedly achieved a breakthrough in electronic warfare, testing an AI-powered airborne radar capable of penetrating heavy jamming while maintaining near-perfect accuracy.
The technology, a newly tested airborne radar system powered by artificial intelligence, reportedly achieved near-perfect tracking even under sophisticated electronic jamming. If deployed in combat, experts say it could give the People’s Liberation Army (PLA) a powerful edge in electronic warfare.
“If this AI radar performs as described in combat, it could lead to electronic supremacy,” a Beijing-based aerospace expert told the South China Morning Post (SCMP), speaking on condition of anonymity due to the sensitivity of the issue.
China’s AI radar achieves 99% tracking accuracy despite electronic warfare jamming
According to SCMP, the breakthrough was achieved during a flight test of an AI-enhanced radar system aboard an unidentified Chinese military aircraft.
While conventional radar systems struggled to maintain contact with targets, often losing them a quarter of the time, the AI-driven system maintained a detection rate of over 99 per cent.

“Radar target tracking continuity has improved from the original 70 per cent-80 per cent to over 99 per cent,” project lead scientist Zhang Jie of the China Electronics Technology Group Corporation’s 14th Research Institute told SCMP, citing findings published in the Chinese journal Informatisation Research.
Zhang described the innovation as nothing short of transformative: “A paradigm shift in radar design philosophy is on the horizon.”
Cognitive radar: AI system adapts in milliseconds to defeat jamming
What makes this radar different is its cognitive capacity. Instead of merely scanning and reporting, it constantly analyses the electromagnetic environment, identifying jamming efforts, then dynamically shifting frequencies, beam directions and waveforms to sidestep interference. It is, in essence, radar that thinks.
“Existing radar anti-jamming techniques are mainly designed based on static assumptions about the electromagnetic environment, making them often unable to cope with dynamically changing interference conditions,” Zhang told SCMP. “This shortcoming can lead to a significant degradation or even complete failure of radar performance.”

He explained that the new radar is designed to adapt instantly: “By sensing electromagnetic interference in the surrounding environment, the technique adaptively selects operating frequencies and bandwidths, and integrates space-time two-dimensional adaptive processing to maximally avoid interference, thereby greatly improving the radar’s resilience against jamming.”
According to SCMP, if an adversary alters its jamming tactics, the system reconfigures itself in milliseconds, effectively outthinking the enemy on the fly.
PLA overcomes airborne radar limits with AI breakthrough
While the PLA Navy has previously deployed AI-assisted radar on its surface vessels, reportedly allowing them to maintain tracking even under aggressive US electronic suppression, progress on aircraft had been slower due to tight constraints on space, power and processing capacity.
But those barriers appear to have been overcome. The successful airborne trial marks a major turning point, potentially allowing the PLA Air Force to bring advanced AI capabilities into fast, highly mobile combat platforms.
The 14th Research Institute, based in Nanjing, is widely regarded as China’s premier military radar hub and has long played a pivotal role in advancing electronic warfare systems.
China’s AI radar avoids large language models for reliability
Interestingly, Chinese engineers avoided the use of large language models (LLMs), the type of AI made famous by chatbots like ChatGPT, opting instead for traditional machine learning algorithms.
This decision, SCMP notes, reflects a focus on reliability and control, especially important in manned combat systems where unpredictable behaviour is unacceptable.

While LLM-based AI has been integrated into Chinese electronic warfare drones for autonomous signal analysis and jamming, the team behind the radar sought a more interpretable approach for use aboard crewed aircraft.
All results, including algorithm design, simulations and flight data, were rigorously validated, Zhang told SCMP.
China’s AI radar raises fears of ‘one-way transparency’ in electronic warfare
Military analysts say this development reinforces a trend already troubling Western defence planners: the emergence of a Chinese capability for “one-way transparency” in the electromagnetic domain. That is, the ability to observe, jam and target opponents while remaining largely hidden themselves.
The SCMP report cites recent events that have added weight to this concern, including Pakistan’s claim that it downed five Indian fighter jets in May, allegedly with help from Chinese-supplied electronic warfare systems. Among the aircraft reportedly shot down were three Rafales, among the most advanced in India’s arsenal.
For countries like the US and India, such reports only reinforce fears that the PLA is pulling ahead in a warfighting domain that is increasingly central to modern conflict.
AI radar applications beyond defence: Smart cities and civilian use
Beyond its military implications, China’s AI radar technology could revolutionise civilian infrastructure, particularly in urban environments overwhelmed by wireless signals. In smart cities, autonomous vehicles and drones often experience radar interference from the saturated electromagnetic spectrum.

According to SCMP, the same environment-aware capabilities that allow military radar to adapt to hostile interference can be used to improve radar reliability in congested urban areas.
“This technology not only holds broad application prospects in the military domain, but also provides solutions for civilian applications in addressing issues such as spectrum interference,” Zhang said.
Electronic warfare arms race intensifies with AI radar and space jammers
This latest Chinese advance comes amid growing tensions between the US and China over electromagnetic dominance, both on Earth and in orbit.
The US recently began deploying a new network of satellite jammers, known as Remote Modular Terminals (RMTs), in the Indo-Pacific, a move intended to disrupt Chinese satellite communications and surveillance.

American military leaders have admitted that China’s space-based systems, such as the Yaogan satellite series, now offer continuous surveillance capabilities over US forces in the region.
But this push to neutralise Chinese sensors may only accelerate the technological arms race.
Analysts warn that a spiralling contest of invisible weapons such as AI radars, space jammers, electronic decoys, and more could soon define modern warfare more than missiles or aircraft.