Regular Articles

Full Text / References

Prediction of Plasma Confinement Indices by Gaussian Process Regression

Sora YABUMOTO¹⁾, Shinsuke SATAKE^1,2), Hiroyuki YAMAGUCHI^1,2)

1)

The Graduate University for Advanced Studies, SOKENDAI, 322-6 Oroshi-cho, Toki, Gifu 509-5292, Japan

2)

National Institute for Fusion Science, National Institutes of Natural Sciences, 322-6 Oroshi-cho, Toki 509-5292, Japan

(Received 12 June 2024 / Accepted 18 February 2025 / Published 17 June 2025)

Abstract

To optimize the design of a helical fusion reactor by varying the shape of the magnetic coils, several requirements related to the performance of the reactor should be satisfied under various constraints. To address this multi-objective optimization problem, we utilized Gaussian process regression (GPR) for machine learning to develop a surrogate model capable of predicting the dependence of the objective functions on the parameters representing the coil shape. This study demonstrates that the dependence of objective functions, such as plasma volume and the Mercier criterion, on the shape of helical coil windings can be predicted by GPR.

Copyright (c) 2025 The Japan Society of Plasma Science and Nuclear Fusion Research

Keywords

fusion reactor design, machine learning, Gaussian process, Mercier criterion

DOI: 10.1585/pfr.20.1403026

Full Text

PDF format (6.0Mbytes)

References

• [1] T. Goto et al., Nucl. Fusion 59, 076030 (2019).
• [2] T. Goto et al., Plasma Fusion Res. 16, 1405085 (2021).
• [3] F. Warmer et al., IEEE Trans. Plasma Sci. 44, 1576 (2016).
• [4] Y. Narushima et al., Plasma Fusion Res. 15, 1405076 (2020).
• [5] D.J. Strickler et al., Fusion Sci. Technol. 41, 107 (2002).
• [6] M. Landreman, Nucl. Fusion 57, 046003 (2017).
• [7] P. Helander, Rep. Prog. Phys. 77, 087001 (2014).
• [8] H. Yamaguchi, Nucl. Fusion 59, 104002 (2019).
• [9] D.A. Gates et al., Nucl. Fusion 57, 126064 (2017).
• [10] C. Zhu et al., Plasma Phys. Control. Fusion 60, 065008 (2018).
• [11] H. Yamaguchi et al., Nucl. Fusion 61, 106004 (2021).
• [12] A. Iiyoshi et al., Nucl. Fusion 39, 1245 (1999).
• [13] H. Yamada et al., Plasma Phys. Control. Fusion 43, A55 (2001).
• [14] H. Tsutsui et al., IEEE Trans. Appl. Supercond. 26, 4901704 (2016).
• [15] S.P. Hirshman et al., Comput. Phys. Commun. 43, 143 (1986).
• [16] S. Yabumoto et al., Plasma Fusion Res. 18, 1403018 (2023).
• [17] M. Landreman, J. Plasma Phys. 86, 905860510 (2020).
• [18] D. Panici et al., Plasma Phys. 89, 955890303 (2023).
• [19] D.P. Kingma and J.L. Ba, arXiv preprint arXiv: 1412.6980 (2014).
• [20] B. Shahriari et al., Proc. IEEE 104 (IEEE, 2016) 148–175.
• [21] H. Imamura and K. Matsui, Bayesian Optimization: Fundamentals and Practice of Adaptive Experimental Design, H. Ohtsuka, (Kindai kagaku sha Co., Ltd, Tokyo, 2023) Section 1.3. [in Japanese]