用神经随机延迟微分方程建模不规则天文时间序列
Modeling Irregular Astronomical Time Series with Neural Stochastic Delay Differential Equations
- 结合神经网络与随机延迟微分方程，捕捉时间延迟动态
- 在稀疏噪声数据上实现高分类准确率和新天体现象检测
- 适合处理观测不完整、采样不规则的天文数据研究者
来自大规模巡天（如LSST）的天文时间序列常为不规则采样且不完整，给分类与异常检测带来挑战。我们提出基于神经随机延迟微分方程（Neural SDDEs）的新框架，融合随机建模与神经网络，以捕捉延迟时间动态并处理不规则观测。方法包含延迟感知神经架构、SDDE数值求解器，以及在噪声稀疏序列中稳健学习的机制。在不规则采样天文数据上的实验表明，该方法在部分标签情况下仍能实现高分类精度，并有效检测新型天体物理事件。本工作展示了Neural SDDEs在观测受限条件下的时间序列分析中具有理论合理性与实际应用价值。
原文摘要 · Abstract (English)
Astronomical time series from large-scale surveys like LSST are often irregularly sampled and incomplete, posing challenges for classification and anomaly detection. We introduce a new framework based on Neural Stochastic Delay Differential Equations (Neural SDDEs) that combines stochastic modeling with neural networks to capture delayed temporal dynamics and handle irregular observations. Our approach integrates a delay-aware neural architecture, a numerical solver for SDDEs, and mechanisms to robustly learn from noisy, sparse sequences. Experiments on irregularly sampled astronomical data demonstrate strong classification accuracy and effective detection of novel astrophysical events, even with partial labels. This work highlights Neural SDDEs as a principled and practical tool for time series analysis under observational constraints.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。