The paper reports on the integration and testing of neural‑network emulators that predict plasma shape for the MAST‑Upgrade tokamak’s plasma control system. The neural models use plasma current, poloidal field coil currents, and plasma profile parameters to output shape predictions and Jacobians, which are then used by a real‑time C++ inference server to compute virtual circuit matrices and updated coil current requests. The work emphasizes a validation workflow and best practices to build confidence in the AI‑based control framework before experimental deployment.
By Matthew J. Marshall, Edward Jones, Graham J. McArdle, Alasdair Ross, Kamran Pentland, Nicola C. Amorisco, Charles Vincent, Martin Kochan, Colin Hogben, Graham Jones, Adam Stephen, George K. Holt, Adriano Agnello
arXiv:2608.23217v1 Announce Type: cross
Abstract: Fast and reliable plasma equilibrium prediction is essential for real-time tokamak operation and control, but conventional Grad-Shafranov (GS) solver...
By Guoyang Shi, Zitong Zhang, Siqi Ding, Jianguo Chen, Yapeng Zhang, Jiayi Zhi, Hanyue Zhao, Tianyuan Liu
arXiv:2606. 15512v1 Announce Type: new Abstract: Real-time reconstruction of magnetohydrodynamic equilibria is essential for plasma shaping, stability assessment and feedback control in magnetic confinement fusion.
By Jay Phil Yoo, William Howes, Yashika Ghai, Kazuma Kobayashi, Souvik Chakraborty, Syed Bahauddin Alam
Fast and reliable plasma equilibrium prediction is essential for real-time tokamak operation and control, but conventional Grad-Shafranov (GS) solvers are often too costly for real-time deployment. We...
arXiv:2605. 05857v2 Announce Type: replace Abstract: Tokamaks remain leading candidates for achieving practical fusion energy, yet many important control problems inside these devices are still difficult or unsolved.
By Rohit Sonker, Hiro Josep Farre Kaga, Jiayu Chen, Andrew Rothstein, Ian Char, Ricardo Shousha, Egemen Kolemen, Jeff Schneider
arXiv:2607. 21407v1 Announce Type: cross Abstract: The boundary and divertor plasma govern how a tokamak exhausts power and particles, setting heat fluxes, target conditions, and the onset of detachment.
By Abdourahmane Diaw, Sebastian De Pascuale, Jae-Sun Park, Ivan Paradela Perez, Jeremy D. Lore, Stefan Dasbach
The paper presents an end‑to‑end workflow for deploying a recurrent probabilistic neural network (RPNN) on FPGA hardware to enable real‑time plasma state estimation for Tokamak control. By reducing architecture size and applying quantization‑aware training with QKeras, the model is synthesized with hls4ml for a Xilinx Alveo U50 device, achieving deterministic sub‑10 µs single‑timestep latency while staying within all four resource budgets (DSP, LUT, FF, BRAM).
By Daniel Gaytan-Villarreal, Aiken Xie, Tu Pham, Rohit Sonker, Chiara Amendola, Matteo Cremonesi, Cong Hao, Jeff Schneider
The paper presents a probabilistic neural surrogate for scrape‑off‑layer (SOL) plasma simulations in tokamaks. By mapping the curvilinear SOLPS‑ITER mesh to three fixed‑size image tensors, the authors preserve geometric adjacency and enable a convolutional network to process the mesh without loss of information. A conditional flow‑matching model is trained on this representation, producing efficient, scalable predictions that capture multiple plausible outcomes—such as distinct hot and cold modes—near the divertor detachment transition and correctly recover known bifurcations in synthetic data.
By Gabriele Gianuzzo, Stefan Dasbach, Fleur Hendriks, Sven Wiesen, Vlado Menkovski
arXiv:2606. 07550v1 Announce Type: cross Abstract: Offline reinforcement learning (RL) offers a promising route for developing plasma controllers from historical tokamak data, since online trial-and-error on real devices is costly and risky.
By Yang Fu, Haomin Bao, Rohit Sonker, Xiaoyan Hu, Aravind Venugopal, Jeff Schneider, Jiayu Chen
The study presents a reinforcement learning approach, Advantage Aggregation (AdvA), to control the X‑point target (XPT) divertor in the EXL‑50U tokamak experiment. By preserving objective‑wise temporal credit and applying a residual correction, AdvA‑PPO outperforms standard Reward‑PPO and a feedforward‑plus‑PID baseline, achieving a 0.81 worst‑channel score and reducing X‑point flux RMSE by roughly 20× over a 500 ms rollout. The method remains robust under measurement uncertainties and across varied initial equilibria, offering a simulation‑based foundation for future real‑time XPT validation on EXL‑50U.
By Siqi Ding, Xuanhe Wang, Pei Guo, Guoyang Shi, Changquan Yu, Yiting Wang, Xianming Song, Xiang Gu, Zhengyuan Chen, Lei Xing, Yapeng Zhang, Jianguo Chen, Tianyuan Liu
GyroSwin is a scalable 5‑dimensional neural surrogate that models nonlinear gyrokinetic plasma turbulence, a key challenge for nuclear fusion research. It extends Vision Transformers to 5D, incorporates cross‑attention and latent 3D↔5D interactions, and uses channelwise mode separation inspired by nonlinear physics. The model outperforms traditional reduced numerics in heat‑flux prediction, captures turbulent energy cascades, and cuts the computational cost of full gyrokinetic simulations by three orders of magnitude while remaining physically verifiable.
By Fabian Paischer, Gianluca Galletti, William Hornsby, Paul Setinek, Lorenzo Zanisi, Naomi Carey, Stanislas Pamela, Johannes Brandstetter
Fast surrogates for tokamak boundary-plasma simulation are typically deterministic regressors mapping a global operating point to a flattened vector of cell values. Near the divertor detachment transi...