The International Atomic Energy Agency (IAEA) has designated the Centre for Science of Information at Purdue University in the USA as the first IAEA Collaborating Centre to support Agency activities on artificial intelligence (AI) for nuclear power applications, including reactor design, plant operations, and training and education.

As a result of rapid progress in computational resources and data analysis tools, the nuclear industry has already started to benefit from AI, including with machine learning techniques that can streamline NPP operations and maintenance. AI is also supporting the development of advanced nuclear power technologies such as small modular reactors (SMRs).

“With more and more countries looking to nuclear energy to address climate change and sustainable development, this Collaborating Centre will provide much needed support for our member states in using AI to advance the innovation driving the global nuclear sector,” said Mikhail Chudakov, IAEA Deputy Director General and Head of the Department of Nuclear Energy.

The five-year Collaborating Centre agreement will support IAEA programmatic activities and knowledge sharing on advancements and innovation in AI for nuclear power. This includes IAEA initiatives on benchmark exercises for developing confidence and community-wide acceptance of Al technology for nuclear power. This establishes a "benchmarking hub" for coordination and data management, as well as other activities relevant to the development and assessment of Al technologies in collaboration with IAEA member states.

IAEA says AI offers the potential to optimise numerous processes within NPPs. It could be used to bolster efficiency and ensure a steady electricity supply by adjusting power generation based on real-time data, including consumer demand, weather and equipment performance. Automation using robotics and AI systems could handle routine tasks, reducing the need for human input. AI could also improve fuel efficiency and maximise the energy output of reactors.

“This Collaborating Centre will help build confidence in AI applications for high consequence systems, such as nuclear reactors, said Hany Abdel-Khalik, Professor of Nuclear Engineering at the Centre for Science of Information, which advances information theory through collaborative research and teaching. “Without reliable quantification, the nuclear community's ability to realize the potential of AI will be diminished and this will negatively impact its ability to remain competitive in the energy market.”

The Collaborating Centre agreement is part of recent IAEA efforts to strengthen support to countries interested in using AI for nuclear science and technology. A 2022 IAEA publication reviewed the challenges and priorities for future AI activities, including those relevant to nuclear power as well as nuclear sciences and applications, among others. The IAEA’s International Network on Innovation to Support Operating Nuclear Power Plants (ISOP) is examining the regulatory and technical aspects of AI deployment. Several coordinated research projects related to AI are underway. Another is to be launched on how AI and other innovative technologies proposed for SMRs can be secured.

The agreement with Purdue University comes after the Agency recently designated the Massachusetts Institute of Technology (MIT) Plasma Science and Fusion Centre as the first Collaborating Centre focused on accelerating fusion research, with an emphasis on AI applications to advance the IAEA’s AI for Fusion initiative.