A technical road map that natively embeds artificial intelligence across the full life cycle of advanced nuclear energy systems was unveiled on July 17 at the 2026 World Artificial Intelligence Conference (WAIC) in Shanghai, aiming to address one of the most challenging issues in industrial AI — deploying AI algorithms in fields with zero tolerance for safety failures.

The "AI for ADANES" road map was released at a forum titled "AI and Advanced Nuclear Energy for a Sustainable Intelligent Future", organized by the Institute of Modern Physics of the Chinese Academy of Sciences. It was the first WAIC forum dedicated to integrating AI with nuclear energy, bringing together discussions on AI, advanced nuclear systems, zero-carbon computing, and energy security.

ADANES, short for Accelerator-Driven Advanced Nuclear Energy System, is a CAS-developed platform that integrates nuclear fuel breeding, spent-fuel transmutation, and power generation. Its subcritical operating mode fundamentally changes the safety logic of conventional nuclear reactors while introducing new challenges in system coupling and long-term stable operation.

CiADS, a major national science and technology infrastructure currently under construction, serves as the engineering verification platform for ADANES.

Against this backdrop, the roadmap establishes a "triple-driving" paradigm that integrates data, physics-based models, and expert knowledge, according to Zhan Wenlong, chief commander of the ADANES project and an academician of the Chinese Academy of Sciences.

He Yuan, deputy director of the Institute of Modern Physics and technical director of ADANES, said the approach aims to reconcile the opacity and unpredictability of black-box AI systems with the nuclear industry's stringent safety requirements, offering a framework for deploying AI in advanced nuclear energy systems.

The AI architecture comprises five layers — a unified data infrastructure, physics-native world models, physical-system control, intelligent-agent coordination, and continuous evolution — that embed AI across the system's full life cycle, from design and commissioning to operation and maintenance.

Wang Shoujun, president of the Chinese Nuclear Society, said the digital and intelligent transformation of the nuclear industry is an "inevitable trend" in achieving high-quality development.

"AI will play a central role throughout the entire life cycle of nuclear energy by improving quality, efficiency, and safety," Wang said, adding that nuclear power can also provide a stable, zero-carbon energy foundation for the AI industry.

Source: China Daily