标题： 基于对比表示学习的极不平衡多变量时间序列数据太阳耀斑预测 显示英文标题

标题： Contrastive Representation Learning for Predicting Solar Flares from Extremely Imbalanced Multivariate Time Series Data

摘要： 强太阳耀斑是太阳磁场通量的突然激增，对技术基础设施构成重大风险。 鉴于此，在空间天气研究中，通过机器学习方法有效预测太阳活动区磁场数据中的强耀斑变得尤为重要。 磁场数据可以表示为多元时间序列模式，在这种模式下，由于强耀斑事件的稀有性，数据呈现出极端的类别不平衡。 在基于时间序列分类的耀斑预测中，对比表示学习方法的应用相对有限。 本文介绍了一种名为CONTREX的新颖对比表示学习方法，用于多元时间序列数据，解决了时间依赖性和极端类别不平衡的挑战。 我们的方法涉及从多元时间序列实例中提取动态特征，从正负类特征向量中推导出两个极端点，这些极端点提供了最大的分离能力，并通过我们提出的新型对比重建损失来训练序列表示嵌入模块，以生成与极端点对齐的嵌入。 这些嵌入捕捉了时间序列的关键特征并增强了辨别能力。 我们的方法在Space Weather Analytics for Solar Flares (SWAN-SF)多元时间序列基准数据集上对基线方法展示了有前景的太阳耀斑预测结果。 显示英文摘要

摘要： Major solar flares are abrupt surges in the Sun's magnetic flux, presenting significant risks to technological infrastructure. In view of this, effectively predicting major flares from solar active region magnetic field data through machine learning methods becomes highly important in space weather research. Magnetic field data can be represented in multivariate time series modality where the data displays an extreme class imbalance due to the rarity of major flare events. In time series classification-based flare prediction, the use of contrastive representation learning methods has been relatively limited. In this paper, we introduce CONTREX, a novel contrastive representation learning approach for multivariate time series data, addressing challenges of temporal dependencies and extreme class imbalance. Our method involves extracting dynamic features from the multivariate time series instances, deriving two extremes from positive and negative class feature vectors that provide maximum separation capability, and training a sequence representation embedding module with the original multivariate time series data guided by our novel contrastive reconstruction loss to generate embeddings aligned with the extreme points. These embeddings capture essential time series characteristics and enhance discriminative power. Our approach shows promising solar flare prediction results on the Space Weather Analytics for Solar Flares (SWAN-SF) multivariate time series benchmark dataset against baseline methods.