The preparation and construction of new tokamaks in the world such as ITER, BEST, and in the more distant future the projects of future fusion reactors like DEMO and CFEDR, will change the landscape of data visualization. Indeed, current plasma discharges last a few minutes at most, whereas data from future fusion machines will be collected over hours. A new era is beginning, particularly for the visualization and analysis of physical phenomena: how to focus on the interesting periods of the discharge and how to quickly store and analyze all this data? This is the challenge of this workshop, which brings together different experts in the analysis and visualization of datasets.
The workshop aims to bring the fusion community together to discuss the challenges posed by AI and the visualization of large datasets in fusion experiments and simulations.
The three-day in hybrid event focuses on feedback, lessons learned, and innovative techniques that developers and users experience with AI techniques and large dataset visualization. A summary of the workshop with all contributors for a journal is one of the key outcomes.
The workshop took place at the Princeton University, Mader Hall.
The manuscript should be concise to synthesize the key points from the workshop presentations. The final Research Topic will group all the contributions, with a global introduction, conclusions, perspectives, and recommendations for the future.
Important Note: Please note that submissions to the Research Topic are by invitation only; uninvited manuscripts will be moved outside of this topic and treated as regular submissions to the section Fusion Plasma Physics.
Keywords:
AI, Machine learning, visualization, neural network, Real time, digital twins
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
The preparation and construction of new tokamaks in the world such as ITER, BEST, and in the more distant future the projects of future fusion reactors like DEMO and CFEDR, will change the landscape of data visualization. Indeed, current plasma discharges last a few minutes at most, whereas data from future fusion machines will be collected over hours. A new era is beginning, particularly for the visualization and analysis of physical phenomena: how to focus on the interesting periods of the discharge and how to quickly store and analyze all this data? This is the challenge of this workshop, which brings together different experts in the analysis and visualization of datasets.
The workshop aims to bring the fusion community together to discuss the challenges posed by AI and the visualization of large datasets in fusion experiments and simulations.
The three-day in hybrid event focuses on feedback, lessons learned, and innovative techniques that developers and users experience with AI techniques and large dataset visualization. A summary of the workshop with all contributors for a journal is one of the key outcomes.
The workshop took place at the Princeton University, Mader Hall.
The manuscript should be concise to synthesize the key points from the workshop presentations. The final Research Topic will group all the contributions, with a global introduction, conclusions, perspectives, and recommendations for the future.
Important Note: Please note that submissions to the Research Topic are by invitation only; uninvited manuscripts will be moved outside of this topic and treated as regular submissions to the section Fusion Plasma Physics.
Keywords:
AI, Machine learning, visualization, neural network, Real time, digital twins
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.