China develops AI to detect F-22 and F-35 heat signatures

Researchers from the Beijing Institute of Technology and the China Airborne Missile Academy have developed a lightweight artificial intelligence system designed to help air-to-air missiles identify the infrared signatures of fifth-generation stealth fighters, such as the U.S. F-22 Raptor and F-35 Lightning II.

While stealth aircraft are designed to evade radar, they still emit heat through engine exhaust and aerodynamic friction. The AI model aims to distinguish these specific thermal signatures from decoys like flares. In simulated laboratory tests, the system achieved a recognition accuracy of up to 97.1 percent for identifying these aircraft, with separate tests showing approximately 90 percent accuracy.

The development addresses the technical challenge of implementing deep-learning models within the strict constraints of missile hardware, which faces significant limitations regarding computing power, weight, and physical space. The researchers trained the system using a dataset of 3,245 infrared images. Lead researcher An Jiangshan noted that the specific test data used remains confidential.