2025/10/28 by Qianyun Dong, Rongpeng Li, Dong, Qianyun +12
#physics.plasm-ph
paper · pdf · doi:10.48550/arxiv.2510.24347
The Multifaceted Asymmetric Radiation From the Edge (MARFE) is a critical plasma instability that often precedes density-limit disruptions in tokamaks, posing a significant risk to machine integrity and operational efficiency. We develop a physics-gated, continuous MARFE monitor for the HL-3 tokamak that outputs a per-frame intensity probability every 2 ms, which can potentially be used by the shape-target controller in the plasma control system. Our framework integrates two core innovations: (1) a physics-scored, weighted Expectation-Maximization (EM) pipeline that refines noisy visual labels using (ne, Te, fG, t) as a Bayesian prior, and (2) a continuous-time, physics-gated Neural Ordinary Differential Equation (Neural ODE) backbone whose dynamics are modulated by a sigmoid gate on fG and Te. Meanwhile, the Neural ODE adopts a 40 ms forward forecasting horizon to accommodate the actuator-response budget. On a frozen 140-shot held-out test set, the proposed method yields a median label-aligned lead time of +36 ms, close to this design horizon. Against a Bi-LSTM baseline trained under the matched protocol, the proposed Neural ODE attains Area Under the Curve (AUC) =0.981 and sample-level F1=0.840, compared with AUC =0.960 and sample-level F1=0.779 for the baseline. The deployed inference service runs within a 1-ms control-cycle budget, while new diagnostic samples are generated at the 2-ms frame cadence.