TLS方法用于托卡马克破裂预警：在DIII-D和EAST上优于DSM
Horizon-Aware Early Event Prediction for Tokamak Disruption Alarms
托卡马克最怕等离子体突然破裂，这篇论文把生存模型改成只看有限时间窗，TLS 在 DIII-D 和 EAST 上报警最准。
研究将早期事件预测（EEP）目标引入基于生存分析的托卡马克破裂预警，以 Deep Survival Machines（DSM）为全分布基线，在 DIII-D、Alcator C-Mod 和 EAST 三个装置上对比 TLS 与 survTLS 两种方法。结果显示 TLS 在 DIII-D 和 EAST 上取得最佳平均报警表现，而所有方法在 Alcator C-Mod 上表现都不理想。survTLS 并未稳定超过 DSM，说明在当前设置下直接学习视界内破裂概率比建模视界内事件时间分布更有效。所选预测视界和编码器消融结果随装置不同而变化，反映出各装置破裂特性的差异。
Horizon-Aware Early Event Prediction for Tokamak Disruption Alarms
Reliable disruption prediction is essential for the safe operation of future tokamaks. Existing full-distribution survival methods model the complete residual time-to-disruption distribution, whereas operational decisions primarily depend on disruption risk within a finite prediction horizon. This mismatch motivates introducing Early Event Prediction (EEP) objectives into survival-based disruption prediction. We take Deep Survival Machines (DSM) as the full-distribution baseline and propose applying two established EEP methods to tokamak disruption prediction: Temporal Label Smoothing (TLS), which directly predicts disruption probability within a finite horizon, and survTLS, which additionally models the event-time distribution within that horizon. Using a common causal encoder, we compare these methods on DIII-D, Alcator C-Mod, and EAST. We distinguish threshold-free deadline ranking from validation-selected fixed-policy alarm performance and evaluate prediction horizons and encoder architectures. TLS achieves the best mean alarm performance on DIII-D and EAST, whereas all methods perform poorly on Alcator C-Mod. survTLS does not consistently outperform DSM, suggesting that directly learning horizon-level event probability is more effective than modeling detailed within-horizon event-time distributions in the present setting. Finally, the selected prediction horizons and encoder-ablation results vary across devices, reflecting differences in disruption characteristics.
