Neural-Parareal: Dynamically Training Neural Operators as Coarse Solvers for Time-Parallelisation of Fusion MHD Simulations

• Published in: arXiv.org
• Main Authors: Pamela, S J P, Carey, N, Brandstetter, J, Akers, R, Zanisi, L, Buchanan, J, Gopakumar, V, Hoelzl, M, Huijsmans, G, Pentland, K, James, T, Antonucci, G, the JOREK Team
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 02.05.2024
• Subjects: Algorithms; Computer simulation; Design engineering; Design optimization; Industrial energy; Neural networks; Nuclear power plants; Nuclear research; Operators; Parallel processing; Physics - Plasma Physics; Research facilities; Simulation; Solvers

The fusion research facility ITER is currently being assembled to demonstrate that fusion can be used for industrial energy production, while several other programmes across the world are also moving forward, such as EU-DEMO, CFETR, SPARC and STEP. The high engineering complexity of a tokamak makes...