Ordinal Encoding as a Regularizer in Binary Loss for Solar Flare Prediction
Chetraj Pandey, Jinsu Hong, Anli Ji, Rafal A. Angryk, Berkay Aydin
太阳耀斑的预测通常被表述为二元分类任务,根据指定的阈值(例如,大于或等于C级,M级或X级)将事件区分为Flare(FL)或No-Flare(NF)。 然而,这个二进制框架忽略了每个类别(FL和NF)中包含的子类之间的固有序关系。 关于太阳耀斑预测的几项研究从经验上表明,最常见的错误分类发生在这个预测阈值附近。 这表明模型难以区分强度相似但落在二进制阈值相反侧的事件。 为了减轻这种限制,我们提出了一个修改的损失函数,它将二进制耀斑标签子类之间的序信息集成到传统的二进制交叉熵(BCE)损失中。 这种方法是一种具有正则意识,数据驱动的正则化方法,比模型优化期间远离边界的预发素事件更严重地惩罚了靠近预测阈值的照明弹事件的错误预测。 通过将有序加权纳入损失函数,我们的目标是通过利用数据的有序特性来增强模型的学习过程,从而提高其整体性能。
The prediction of solar flares is typically formulated as a binary classification task, distinguishing events as either Flare (FL) or No-Flare (NF) according to a specified threshold (for example, greater than or equal to C-class, M-class, or X-class). However, this binary framework neglects the inherent ordinal relationships among the sub-classes contained within each category (FL and NF). Several studies on solar flare prediction have empirically shown that the most frequent misclassifications...
