Search NASA⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 3027568

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

Wang, Allen M. [Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)] (ORCID:0000000216523354)·Pau, Alessandro [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)] (ORCID:0000000271223346)·Rea, Cristina [Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)]·So, Oswin [Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)]·Dawson, Charles [Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)]·Sauter, Olivier [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)] (ORCID:0000000200996675)·Boyer, Mark D. [Commonwealth Fusion Systems, Devens, MA (United States)]·Vu, Anna [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)]·Galperti, Cristian [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)]·Fan, Chuchu [Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)]·Merle, Antoine [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)]·Poels, Yoeri [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)] (ORCID:0000000240714855)·Venturini, Cristina [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)]·Felici, Federico [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)]·Marchioni, Stefano [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)]
View original source ↗Read source document ↗Export metadata ↓

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.

Explore related subjects

70 PLASMA PHYSICS AND FUSION TECHNOLOGY

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Wang, Allen M. [Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)] (ORCID:0000000216523354), Pau, Alessandro [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)] (ORCID:0000000271223346), Rea, Cristina [Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)], So, Oswin [Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)], Dawson, Charles [Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)], Sauter, Olivier [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)] (ORCID:0000000200996675), Boyer, Mark D. [Commonwealth Fusion Systems, Devens, MA (United States)], Vu, Anna [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)], Galperti, Cristian [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)], Fan, Chuchu [Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)], Merle, Antoine [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)], Poels, Yoeri [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)] (ORCID:0000000240714855), Venturini, Cristina [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)], Felici, Federico [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)], Marchioni, Stefano [Ecole Polytechnique Federale Lausanne (EPFL) (Switzerland)]. 2025-10-06. Learning plasma dynamics and robust rampdown trajectories with predict-first experiments at TCV. https://doi.org/10.1038/s41467-025-63917-x

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2026

Fast solvers for tokamak fluid models with PETSc

Multigrid (MG) is widely recognized as a highly effective solver for the model problem, the Laplacian, but textbook MG fails on most problems of interest. MG methods have been applied to complex, real-world applications with careful consideration of the physical model and discretization. In this work we develop the first step in applying MG methods to science and engineering relevant magnetohydrodynamics (MHD) tokamak models in the M3D-C1 (https://m3dc1.pppl.gov) fusion energy science code. The semi-implicit time integrator in M3D-C1 is composed of many linear solves. The implicit advance of the momentum equation is the most challenging and is the focus of this work. The current production solver in M3D-C1 is a block Jacobi (BJ) preconditioner within a Krylov solver, where blocks group degrees of freedom on planes of constant toroidal coordinate. BJ convergence degrades as the number of planes increases due to the spectral properties of the matrix preconditioned with BJ. The partially magnetic field-aligned, regular toroidal grid structure in M3D-C1 is amenable to semi-coarsening geometric MG in the toroidal direction. This paper develops such a solver and demonstrates competitive performance on a runaway electron model of a SPARC (https://cfs.energy/technology/sparc) disruption, and superior robustness on a stellarator model on which the BJ solver fails to converge.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Final Report: A Multi-Channel Fusion Product

The goal of this project was to measure charged fusion products from the d(d,p)t reaction in MAST-U plasmas as a function of time and position with good energy resolution using a system of up to six charged particle detectors. The data from this new diagnostic will make it possible to determine the neutral beam ion density profile as a function of R, z, and t with reduced model dependency and contribute new information to a global analysis of fast ion diagnostic data needed for the determination of the fast ion distribution function (velocity space tomography).

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Unitary Qubit Lattice Algorithms for Plasma Physics

This final technical report summarizes research conducted under DOE Award DE-SC0021653 to develop unitary Quantum Lattice Algorithms for modeling electromagnetic wave propagation and scattering in complex media, including plasmas. The project developed and validated quantum-inspired formulations of Maxwell's equations that preserve unitary evolution and can be evaluated on classical high-performance computing systems while providing a foundation for future quantum-computing implementations. Major accomplishments include the development of two- and three-dimensional algorithms for electromagnetic scattering; scalable, distributed-memory implementations demonstrated on the Perlmutter supercomputer; formulations for nonlinear lossless fluid dynamics and cold, lossless, inhomogeneous magnetized plasmas; and an explicit quantum algorithm for a time-discretized Lorenz model. Simulations reproduced a range of characteristic wave phenomena, including transient effects that are not readily apparent in conventional frequency-domain studies, demonstrating the effectiveness of the proposed approach for modeling complex electromagnetic and plasma systems. The work establishes a unified theoretical and computational framework for quantum and quantum-inspired simulation and provides a foundation for future implementation on fault-tolerant quantum systems.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗