发表机构
RIKEN AIP; Kyushu University IMI（理化学研究所人工智能研究中心; 九州大学数理学研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对托卡马克破裂报警，提出将早期事件预测目标引入生存模型，比较TLS与survTLS方法，发现直接预测视界内破裂概率的TLS在多数装置上表现最优。
AI 中文摘要
可靠的破裂预测对于未来托卡马克的安全运行至关重要。现有的全分布生存方法对完整的剩余破裂时间分布进行建模，而运行决策主要依赖于有限预测视界内的破裂风险。这种不匹配促使我们将早期事件预测（EEP）目标引入基于生存分析的破裂预测中。我们以深度生存机器（DSM）作为全分布基线，并提出将两种成熟的EEP方法应用于托卡马克破裂预测：时间标签平滑（TLS），它直接预测有限视界内的破裂概率；以及survTLS，它额外对该视界内的事件时间分布进行建模。使用共同的因果编码器，我们在DIII-D、Alcator C-Mod和EAST上对这些方法进行了比较。我们区分了无阈值的截止时间排序与验证选择的固定策略报警性能，并评估了预测视界和编码器架构。TLS在DIII-D和EAST上取得了最佳的平均报警性能，而所有方法在Alcator C-Mod上表现均不佳。survTLS并未持续优于DSM，这表明在当前设置下，直接学习视界级事件概率比建模视界内详细的事件时间分布更有效。最后，所选的预测视界和编码器消融结果在不同装置间存在差异，反映了破裂特征的差异。
英文摘要
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.
