AI 中文总结
该研究提出统一框架，用证据网络进行贝叶斯模型比较检测引力微透镜事件，结合神经后验估计推断参数，共享变压器编码器处理不规则采样。在模拟数据上检测效率高、误报率低，在极端区域优势明显，NPE能提供校准后验，助力实时分析。
AI 中文摘要
我们提出了一个用于引力微透镜事件检测和参数推断的统一框架。传统方法在光度统计上使用确定性硬切割，会系统地遗漏有限源区域中的低放大率事件。我们将检测构建为使用证据网络的贝叶斯模型比较，该网络从二元标记模拟中学习校准的贝叶斯因子，并与神经后验估计（NPE）结合进行摊销参数推断。两者共享一个处理不规则采样时间序列而无需插补的变压器编码器。在模拟的罗曼太空望远镜数据上，我们的证据网络在有增强和噪声但无天体物理混杂因素的模拟数据上实现了99.9%的检测效率，误报率低于6×10⁻⁴。在极端有限源区域（ρ≥5）收益最为显著，检测率达到约95%，而硬切割为约65%，这正是对形成场景最具约束性的短持续时间自由漂浮行星事件。我们的NPE提供校准后验，朝着巡天规模的实时分析迈进。
英文摘要
We present a unified framework for gravitational microlensing event detection and parameter inference. Traditional pipelines use deterministic hard cuts on photometric statistics, systematically missing low-magnification events in the finite-source regime. We instead frame detection as Bayesian model comparison using Evidence Networks, which learn calibrated Bayes factors from binary-labeled simulations, and combine this with Neural Posterior Estimation (NPE) for amortized parameter inference. Both share a transformer encoder that handles irregularly-sampled time series without imputation. On simulated Roman Space Telescope data, our Evidence Network achieves $99.9\%$ detection efficiency with a false-positive rate below $6\times10^{-4}$ on simulated data with augmentation and noise, but no astrophysical confounders. Gains are most dramatic in the extreme finite-source regime ($ρ\gtrsim 5$), where detection rates reach ${\sim}95\%$ versus ${\sim}65\%$ for hard cuts, precisely the short-duration free-floating planet events most constraining for formation scenarios. Our NPE provides calibrated posteriors, working towards real-time analysis at survey scale.
CommentsAccepted at ICML 2026 AI for Physics Workshop
