Learning plasma dynamics and robust rampdown trajectories with predict-first experiments at TCV

Allen M. Wang (), Alessandro Pau, Cristina Rea, Oswin So, Charles Dawson, Olivier Sauter, Mark D. Boyer, Anna Vu, Cristian Galperti, Chuchu Fan, Antoine Merle, Yoeri Poels, Cristina Venturini, Federico Felici and Stefano Marchioni
Additional contact information
Allen M. Wang: Massachusetts Institute of Technology
Alessandro Pau: Ecole Polytechnique Fédérale de Lausanne (EPFL)
Cristina Rea: Massachusetts Institute of Technology
Oswin So: Massachusetts Institute of Technology
Charles Dawson: Massachusetts Institute of Technology
Olivier Sauter: Ecole Polytechnique Fédérale de Lausanne (EPFL)
Mark D. Boyer: Commonwealth Fusion Systems
Anna Vu: Ecole Polytechnique Fédérale de Lausanne (EPFL)
Cristian Galperti: Ecole Polytechnique Fédérale de Lausanne (EPFL)
Chuchu Fan: Massachusetts Institute of Technology
Antoine Merle: Ecole Polytechnique Fédérale de Lausanne (EPFL)
Yoeri Poels: Ecole Polytechnique Fédérale de Lausanne (EPFL)
Cristina Venturini: Ecole Polytechnique Fédérale de Lausanne (EPFL)
Federico Felici: Ecole Polytechnique Fédérale de Lausanne (EPFL)
Stefano Marchioni: Ecole Polytechnique Fédérale de Lausanne (EPFL)

Nature Communications, 2025, vol. 16, issue 1, 1-16

Abstract: Abstract The rampdown phase of a tokamak pulse is difficult to simulate and often exacerbates multiple plasma instabilities. To reduce the risk of disrupting operations, we leverage advances in Scientific Machine Learning (SciML) to combine physics with data-driven models, developing a neural state-space model (NSSM) that predicts plasma dynamics during Tokamak à Configuration Variable (TCV) rampdowns. The NSSM efficiently learns dynamics from a modest dataset of 311 pulses with only five pulses in a reactor-relevant high-performance regime. The NSSM is parallelized across uncertainties, and reinforcement learning (RL) is applied to design trajectories that avoid instability limits. High-performance experiments at TCV show statistically significant improvements in relevant metrics. A predict-first experiment, increasing plasma current by 20% from baseline, demonstrates the NSSM’s ability to make small extrapolations. The developed approach paves the way for designing tokamak controls with robustness to considerable uncertainty and demonstrates the relevance of SciML for fusion experiments.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-63917-x Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-63917-x

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-63917-x

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().