arxiv.org·2026/10/23·Luis Bauer / Annalena Kofler 等
为什么重要 弱监督多示例学习配合 attention 可定位关键区域，对可解释科学预测有参考，但应用面窄。
预测太阳耀斑是一个具有挑战性的空间天气预报问题，可能对地球高层大气产生重大影响，包括干扰无线电通信。我们提出了 Active Region attENtion Aggregation（ARENA），这是一种神经网络架构，可从数量可变的 active-region cutouts 预测太阳耀斑，同时学习识别与预测最相关的区域。
ARENA 在弱监督下使用 multiple-instance learning 进行训练，只需要观测的 flare/no-flare 标签，而不需要指定耀斑来源的标签。因此，学习到的 attention 机制提供了一种定位驱动预测的 active region 的方法，而无需显式来源标注。
ARENA 达到了 0.45 的 heidke skill score，这与其他耀斑预测方法相当。这些结果表明，基于 active region 的聚合可以为太阳耀斑预测提供一种高效且可解释的方法。代码可在 https://github.com/LuisBauer22/ARENA 获取。
Predicting solar flares is a challenging space-weather forecasting problem with potentially significant impacts on Earth's upper atmosphere, including disruptions to radio communications.
We propose Active Region attENtion Aggregation (ARENA), a neural network architecture that predicts solar flares from a variable number of active-region cutouts while learning to identify the region most relevant to the prediction.
ARENA is trained using multiple-instance learning under weak supervision, requiring only a flare/no-flare label for the observation and no labels specifying the flare origin.
The learned attention mechanism therefore provides a means of localizing the active region driving the prediction without explicit origin annotations.
ARENA achieves a heidke skill score of 0.45 which is comparable to other flare prediction approaches.
These results demonstrate that active-region-based aggregation can provide an efficient and interpretable approach to solar flare prediction.
The code is available at https://github.com/LuisBauer22/ARENA.
原版排版与图表 · 手机无法内嵌时可在浏览器打开。PDF 插件内选文不能传给网页助手。