天体瞬变事件的概率数据驱动建模：基于NightLANP的超快速与类别无关光变曲线重建的神经过程家族
Probabilistic Data-Driven Modelling of Astrophysical Transients: The Neural Process Family for Ultrafast and Class-Agnostic Light Curve Reconstruction with NightLANP
- NASA FINESST Fellow
- Department of Physics and Astronomy, University of Delaware（物理与天文学系，德雷克塞尔大学）
- University of Delaware, Data Science Institute（德雷克塞尔大学数据科学研究所）
- Joseph R. Biden, Jr. School of Public Policy and Administration, University of Delaware（德雷克塞尔大学公共政策与行政学院）
- Vera C. Rubin Observatory（维拉·鲁宾天文台）
- Division of Physics, Mathematics, and Astronomy, California Institute of Technology（物理、数学与天文学系，加州理工学院）
- Center for Data Driven Discovery, California Institute of Technology（数据驱动发现中心，加州理工学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对稀疏不规则光变曲线重建问题，提出神经过程家族（以注意力神经过程为例），结合高斯过程的概率框架与深度学习的可扩展性，通过元学习实现跨波段、类别无关的快速推理，在Rubin模拟数据上优于高斯过程和神经网络。
AI中文摘要：
来自地球的天体观测受到天气、环境和科学限制，导致稀疏、不规则的光变曲线。在Vera C. Rubin天文台时空遗产巡天前夕，其数据集为瞬变科学提供了前所未有的机遇。然而，一个关键挑战是其观测节奏——在六个波段上稀疏且不规则，限制了推断。插值有助于缓解这一问题，高斯过程是标准方法，但它们在跨波段相关性上表现不佳，需要先验核函数指定，并且必须单独拟合每条光变曲线，因此可扩展性差。在此，我们引入神经过程家族用于光变曲线重建，结合了高斯过程的概率框架与深度学习的可扩展性。通过在多样化的模拟瞬变事件上进行元学习，注意力神经过程将大部分计算转移到训练阶段，从而能够使用类别无关模型进行快速、摊销的推断。在15个瞬变类别上使用真实的Rubin观测节奏进行评估，我们表明，即使是一个未优化的、开箱即用的注意力神经过程，在所有测试指标（包括回归质量、天体物理特征恢复和概率校准）上始终优于所有基准——一组高斯过程和神经网络。我们的模型同时插值所有波段，耗时微秒级，比次优的神经基准快四个数量级，比高斯过程快五个数量级，展示了神经过程在Rubin夜间警报流中的潜力。注意力神经过程避免了标准神经网络的过度自信和高斯过程的信心不足，提供了尖锐且良好校准的不确定性。这项工作确立了神经过程家族作为Rubin时代实时瞬变科学的可扩展概率基础。
英文摘要：
Astrophysical observations from Earth are subject to weather, environmental, and scientific constraints that lead to sparse, irregular light curves. On the eve of the Vera C. Rubin Observatory Legacy Survey of Space and Time, its dataset offers unprecedented opportunities for transient science. Yet a key challenge remains its cadence, sparse and irregular across six bands, limiting inference. Interpolation helps mitigate this, with Gaussian Processes the standard, but they struggle with cross-band correlations, require a priori kernel specification, and must be fit to each light curve individually, hence scaling poorly. Here, we introduce the neural process family for light curve reconstruction, combining the probabilistic framework of Gaussian Processes with the scalability of deep learning. By meta-learning on diverse simulated transients, Attentive Neural Processes shift the bulk of computation to training, enabling rapid, amortized inference with a class-agnostic model. Evaluated on realistic Rubin cadences across 15 transient classes, we show that even an unoptimized, out-of-the-box Attentive Neural Process consistently outperforms all benchmarks -- a suite of Gaussian Processes and neural networks -- on every tested metric, spanning regression quality, astrophysical feature recovery, and probabilistic calibration. Our model interpolates all bands simultaneously in microseconds, over four orders of magnitude faster than the next-best neural benchmark and five faster than Gaussian Processes, demonstrating the potential of neural processes for the nightly Rubin alert stream. Attentive Neural Processes avoid the overconfidence of standard neural networks and the underconfidence of Gaussian Processes, delivering sharp, well-calibrated uncertainties. This work establishes the neural process family as a scalable, probabilistic foundation for real-time transient science in the Rubin era.
