Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 164 tok/s
Gemini 2.5 Pro 46 tok/s Pro
GPT-5 Medium 21 tok/s Pro
GPT-5 High 27 tok/s Pro
GPT-4o 72 tok/s Pro
Kimi K2 204 tok/s Pro
GPT OSS 120B 450 tok/s Pro
Claude Sonnet 4.5 34 tok/s Pro
2000 character limit reached

Multi-objective Bayesian optimization for design of Pareto-optimal current drive profiles in STEP (2310.02669v3)

Published 4 Oct 2023 in physics.plasm-ph

Abstract: The safety factor profile is a key property in determining the stability of tokamak plasmas. To design the safety factor profile in the United Kingdom's proposed Spherical Tokamak for Energy Production (STEP), we apply multi-objective Bayesian optimisation to design electron-cyclotron heating profiles. Bayesian optimisation is an iterative machine learning technique that uses an uncertainty-aware predictive model to choose the next designs to evaluate based on the data gathered during optimisation. By taking a multi-objective approach, the optimiser generates sets of solutions that represent optimal tradeoffs between objectives, enabling decision makers to understand the compromises made in each design. The solutions from our method score higher than those generated in previous work by a genetic algorithm; however, the key result is that our method returns a purposefully diverse range of optimal solutions, providing more information to tokamak designers without incurring additional computational cost.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (19)
  1. M. L. Walker, P. De Vries, F. Felici, and E. Schuster, “Introduction to tokamak plasma control,” in American Control Conference, 2020, pp. 2901–2918.
  2. G. Cenacchi and A. Taroni, “JETTO: a free-boundary plasma transport code,” European Nuclear Energy Authority, Tech. Rep., 1988.
  3. S. Marsden, F. Casson, B. Patel, E. Tholerus, and T. Wilson, “Using genetic algorithms to optimise current drive in STEP,” in Europhysics Conference Abstracts, vol. 46A, 2022, p. P2b.123.
  4. T. Nunn, V. Gopakumar, and S. Kahn, “Shaping of magnetic field coils in fusion reactors using Bayesian optimisation,” in NeurIPS Workshop on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems, 2022.
  5. H. Meyer, “The physics of the preferred plasma scenario for STEP,” in Europhysics Conference Abstracts, vol. 46A, 2022, p. O2.107.
  6. D. Kennedy, M. Giacomin, F. J. Casson, D. Dickinson, W. A. Hornsby, B. S. Patel, and C. M. Roach, “Electromagnetic gyrokinetic instabilities in the Spherical Tokamak for Energy Production (STEP) part I: linear physics and sensitivity,” 2023. [Online]. Available: arxiv.org/abs/2307.01670
  7. J. E. Menard, M. Bell, R. Bell, D. Gates, S. Kaye, B. LeBlanc, S. Sabbagh, E. Fredrickson, S. Jardin, R. Maingi et al., “Unified ideal stability limits for advanced tokamak and spherical torus plasmas,” Princeton Plasma Physics Laboratory, United States, Tech. Rep., 2003.
  8. J. Connor, T. Fukuda, X. Garbet, C. Gormezano, V. Mukhovatov, M. Wakatani et al., “A review of internal transport barrier physics for steady-state operation of tokamaks,” Nuclear Fusion, vol. 44, no. 4, p. R1, 2004.
  9. R. Buttery, B. Covele, J. Ferron, A. Garofalo, C. Holcomb, T. Leonard, J. Park, T. Petrie, C. Petty, G. Staebler et al., “DIII-D research to prepare for steady state advanced tokamak power plants,” Journal of Fusion Energy, vol. 38, no. 1, pp. 72–111, 2019.
  10. S. Mahajan and R. Hazeltine, “Linear theory of electromagnetic instabilities in plasmas with a hollow q-profile,” Nuclear Fusion, vol. 22, no. 9, p. 1191, 1982.
  11. J. Menard, M. Bell, R. Bell, D. Gates, S. Kaye, B. LeBlanc, R. Maingi, S. Sabbagh, V. Soukhanovskii, D. Stutman et al., “Aspect ratio scaling of ideal no-wall stability limits in high bootstrap fraction tokamak plasmas,” Physics of Plasmas, vol. 11, no. 2, pp. 639–646, 2004.
  12. P. Maget, H. Lütjens, R. Coelho, B. Alper, M. Brix, P. Buratti, R. Buttery, E. De la Luna, N. Hawkes, G. Huysmans et al., “Modelling of (2,1) NTM threshold in JET advanced scenarios,” Nuclear Fusion, vol. 50, no. 4, p. 045004, 2010.
  13. H. N. Fitter, A. B. Pandey, D. D. Patel, and J. M. Mistry, “A review on approaches for handling Bézier curves in CAD for manufacturing,” Procedia Engineering, vol. 97, pp. 1155–1166, 2014.
  14. S. Daulton, M. Balandat, and E. Bakshy, “Parallel Bayesian optimization of multiple noisy objectives with Expected Hypervolume Improvement,” in Advances in Neural Information Processing Systems, 2021.
  15. M. Balandat, B. Karrer, D. Jiang, S. Daulton, B. Letham, A. G. Wilson, and E. Bakshy, “BoTorch: a framework for efficient Monte-Carlo Bayesian optimization,” in Advances in Neural Information Processing Systems, 2020.
  16. S. Iwazaki, S. Takeno, T. Tanabe, and M. Irie, “Failure-aware Gaussian process optimization with regret bounds,” in Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  17. P. J. Fleming, R. C. Purshouse, and R. J. Lygoe, “Many-objective optimization: an engineering design perspective,” in International Conference on Evolutionary Multi-criterion Optimization, 2005, pp. 14–32.
  18. R. Kasimbeyli, Z. K. Ozturk, N. Kasimbeyli, G. D. Yalcin, and B. I. Erdem, “Comparison of some scalarization methods in multiobjective optimization,” Bulletin of the Malaysian Mathematical Sciences Society, vol. 42, p. 1875–1905, 2019.
  19. K. Kandasamy, A. Krishnamurthy, J. Schneider, and B. Póczos, “Parallelised Bayesian optimisation via Thompson sampling,” in Artificial Intelligence and Statistics, 2018.
Citations (4)

Summary

We haven't generated a summary for this paper yet.

Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets

This paper has been mentioned in 1 tweet and received 0 likes.

Upgrade to Pro to view all of the tweets about this paper: