Real-time Tokamak Equilibrium Reconstruction Under Limited Experimental Data via Physics-Grounded Synthetic Pre-training
Abstract
Real-time equilibrium reconstruction is essential for tokamak plasma control. Data-driven surrogates are usually trained on high-quality labeled experimental data, but producing a large amount of labeled data sufficient for surrogate learning requires many expensive discharge shots, and few exist at the start of a new campaign or the operation of a new device. To reduce this cost, we propose to pre-train on simulated equilibria, generated at low cost by physics-based simulation, then fine-tune on limited real data. We evaluate under three settings with increasing difficulties, i.e., in-distribution, out-of-distribution (shape), and cross-campaign (temporal) splits, which mirror how reconstruction is actually deployed. Experimental results validate that synthetic pre-training is highly effective when few real labels are available: fine-tuning on only 1% of the full available real dataset cuts the per-sample normalized root-mean-square error (nRMSE) of the reconstructed poloidal flux by roughly 58% under out-of-distribution shapes and 64% under cross-campaign extrapolation, compared to a model trained from scratch on the same amount of real data. These realistic evaluations show that synthetic pre-training improves equilibrium reconstruction accuracy in the data-scarce regime that real tokamak campaigns face.
Related
- Experimental validation of a fast control-oriented, physics-informed surrogate model for plasma equilibrium reconstruction in the TCV tokamak
- Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering
- Diffusion prior for KSTAR equilibrium reconstruction under sensor dropout
- Do Better Scores Mean Better Physics? Physics-Grounded Explanations for Sim2Real Neural Operators
- Physics-Grounded Simulation Enables Zero-Shot Molecular and Reaction Analysis in Scanning Tunneling Microscopy
BibTeX
@misc{he2026realtime,
title = {{Real-time Tokamak Equilibrium Reconstruction Under Limited Experimental Data via Physics-Grounded Synthetic Pre-training}},
author = {Mingdong He and Qixian Hu and Tengfei Xu and Tailin Wu and Zheng Xiong},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.09674},
eprint = {2610.09674},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.09674},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Real-time Tokamak Equilibrium Reconstruction Under Limited Experimental Data via Physics-Grounded Synthetic Pre-training
AU - Mingdong He
AU - Qixian Hu
AU - Tengfei Xu
AU - Tailin Wu
AU - Zheng Xiong
PY - 2026
DA - 2026/10/07
PB - arXiv
DO - 10.48550/arxiv.2610.09674
UR - https://arxiv.org/abs/2610.09674
AB - Real-time equilibrium reconstruction is essential for tokamak plasma control. Data-driven surrogates are usually trained on high-quality labeled experimental data, but producing a large amount of labeled data sufficient for surrogate learning requires many expensive discharge shots, and few exist at the start of a new campaign or the operation of a new device. To reduce this cost, we propose to pre-train on simulated equilibria, generated at low cost by physics-based simulation, then fine-tune on limited real data. We evaluate under three settings with increasing difficulties, i.e., in-distribution, out-of-distribution (shape), and cross-campaign (temporal) splits, which mirror how reconstruction is actually deployed. Experimental results validate that synthetic pre-training is highly effective when few real labels are available: fine-tuning on only 1% of the full available real dataset cuts the per-sample normalized root-mean-square error (nRMSE) of the reconstructed poloidal flux by roughly 58% under out-of-distribution shapes and 64% under cross-campaign extrapolation, compared to a model trained from scratch on the same amount of real data. These realistic evaluations show that synthetic pre-training improves equilibrium reconstruction accuracy in the data-scarce regime that real tokamak campaigns face.
ER -