The International Atomic Energy Agency (IAEA) has launched a programme to create a platform and network to advance fusion R&D with machine learning and artificial intelligence.
The ‘coordinated research project’ in IAEA jargon with four focussed work packages envisages the development of a number of AI enabling activities to overcome current challenges.
Improved AI-based modelling of plasma dynamics from experimental data and plasma simulations offers the possibility of enabling predictive modelling for real-time monitoring, providing fast results for exploration of designs or providing uncertainty quantification, as well as enhancing analysis of instrumentation data, according to the IAEA.
These methods then have the potential for advancing both magnetic and inertial fusion research and development.
However, challenges include differing data ecosystems across various institutes, which make it difficult to validate data-driven models involving complex multi-scale, multi-physics systems, while another is the sharing of experimental or simulation data due to institutional policies, security and intellectual property issues, or the fear of being scooped.
Additionally, the use of AI requires teamwork and diverse skills in order to design integrated solutions to challenges of growing complexity and interdisciplinarity, at the interface of plasma physics, material science and nuclear engineering.
The work packages for the five-year project are as follows.
Work Package 1. Real-time magnetic fusion energy (MFE) system behaviour prediction, identification and optimisation using AI methods, which aims to establish a multi-machine database of experimental and simulation MFE data for AI-driven applications and increased access to knowledge and information of AI methods for MFE.
Work Package 2. Inertial fusion energy physics (IFE) understanding through simulation, theory and experiment using AI methods, which aims to establish a database of experimental and simulation IFE data for AI-driven applications and increased access to knowledge and information of AI methods for IFE.
Work Package 3. Feasibility of MFE and IFE image database.
Work Package 4. Community engagement and workforce development, with the aim to accelerate community engagement and capacity building, as well as create and provide access to knowledge and information in the area of AI methods applied to fusion R&D.
Interested parties are being sought for the project, with proposals required by July 31.