Explaining Full-disk Deep Learning Model for Solar Flare Prediction using Attribution Methods
Explaining Full-disk Deep Learning Model for Solar Flare Prediction using Attribution Methods
复制标题
DOI：
10.1007/978-3-031-43430-3_5
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Chetraj Pandey;R. Angryk;Berkay Aydin
中科院分区：
文献类型：
--
作者：
Chetraj Pandey;R. Angryk;Berkay Aydin
太阳耀斑是短暂的空间天气事件，对空间和地面技术系统构成重大威胁，因此对其进行精确可靠的预测对于减轻潜在影响至关重要。本文为太阳耀斑预测的深度学习方法研究做出了贡献，主要关注高度被忽视的近翼耀斑，并利用归因方法为模型预测提供事后定性解释。我们提出了一个太阳耀斑预测模型，该模型使用每小时全盘视距磁图图像进行训练，并采用二元预测模式来预测可能在接下来的24小时内发生的m级耀斑。为了解决类不平衡问题，我们采用了数据增强和类加权技术的融合；并使用真实技能统计量（TSS）和海德克技能分数（HSS）来评估我们模型的整体性能。此外，我们应用了三种归因方法，即Guided Gradient-weighted Class Activation Mapping、Integrated Gradients和Deep Shapley Additive explanation，来解释和交叉验证我们模型的预测结果。我们的分析表明，太阳耀斑的全盘预测与活动区（ARs）相关的特征一致。特别是，本研究的主要发现是：(1)我们的深度学习模型实现了平均TSS0.51和HSS0.35，结果进一步证明了预测近翼太阳耀斑的能力；(2)对模型解释的定性分析表明，我们的模型识别并利用全盘磁图中与中心和近翼位置ARs相关的特征进行相应的预测。换句话说，我们的模型可以学习燃烧ARs的形状和纹理特征，即使它们位于近肢区域，这是一种新颖而关键的能力，对业务预测具有重要意义。
Solar flares are transient space weather events that pose a significant threat to space and ground-based technological systems, making their precise and reliable prediction crucial for mitigating potential impacts. This paper contributes to the growing body of research on deep learning methods for solar flare prediction, primarily focusing on highly overlooked near-limb flares and utilizing the attribution methods to provide a post hoc qualitative explanation of the model’s predictions. We present a solar flare prediction model, which is trained using hourly full-disk line-of-sight magnetogram images and employs a binary prediction mode to forecastM-class flares that may occur within the following 24-h period. To address the class imbalance, we employ a fusion of data augmentation and class weighting techniques; and evaluate the overall performance of our model using the true skill statistic (TSS) and Heidke skill score (HSS). Moreover, we applied three attribution methods, namely Guided Gradient-weighted Class Activation Mapping, Integrated Gradients, and Deep Shapley Additive Explanations, to interpret and cross-validate our model’s predictions with the explanations. Our analysis revealed that full-disk prediction of solar flares aligns with characteristics related to active regions (ARs). In particular, the key findings of this study are: (1) our deep learning models achieved an average TSS0.51 and HSS0.35, and the results further demonstrate a competent capability to predict near-limb solar flares and (2) the qualitative analysis of the model’s explanation indicates that our model identifies and uses features associated with ARs in central and near-limb locations from full-disk magnetograms to make corresponding predictions. In other words, our models learn the shape and texture-based characteristics of flaring ARs even when they are at near-limb areas, which is a novel and critical capability that has significant implications for operational forecasting.