用自监督学习识别恒星异常亮度变化，一次凌日也能发现系外行星。
One Transit Is All You Need: Detecting Exoplanets Through Learned Stellar Behaviour with EXOVEIL
- 用Transformer模型学恒星正常亮度，从原始光变曲线中找异常
- 单次凌日探测率达32%（1000 ppm深度），传统方法为0%
- 可跨任务直接应用，适合搜寻罕见或单次凌日行星
本文提出EXOVEIL，一种基于自监督学习的凌日检测系统。该系统通过训练16,499条开普勒光变曲线，学习恒星正常亮度行为，无需相位折叠即可在原始通量时间序列上运行，可检测仅发生一次凌日的行星。采用变压器世界模型预测期望亮度，匹配滤波器结合方差加权提取残差中的凌日信号，再由XGBoost分类器区分行星与伪信号，在开普勒DR25数据集上达到AUC 0.938。在单次凌日注入-恢复测试中，成功回收32%的1000 ppm深度凌日信号，而所有基于分类的方法因设计缺陷得分均为0%。对3,737颗开普勒恒星的盲搜发现了179个新凌日信号，其中46个为单次凌日候选。在未重新训练情况下应用于47颗已确认的TESS行星（PLATO LOPS2区域），实现100%回收率，验证了零样本跨任务迁移能力。在PLATO 25秒采样率下，检测灵敏度可达100 ppm，接近地球类行星探测水平。首次将置信区间预测应用于凌日检测，实测覆盖率为95.9%。系统已开源，可通过pip install exoveil获取预训练权重和候选星表。
原文摘要 · Abstract (English)
I present EXOVEIL, a transit detection system that learns what a star's brightness should look like and flags when reality disagrees. Unlike existing systems that require phase-folded input, EXOVEIL operates on raw flux time series and can detect planets that transit only once.A Transformer world model, trained on 16,499 Kepler light curves with transit-masked self-supervised learning, predicts expected stellar flux. A matched-filter detector with variance weighting extracts transit signals from the prediction residuals. A learned classifier (XGBoost) separates planets from false positives, achieving AUC 0.938 on Kepler DR25. Applied to single-transit injection-recovery, EXOVEIL recovers 32% of transits at 1000 ppm depth a task where all classification-based systems score 0% by construction. A blind search of 3,737 Kepler stars yields 179 new transit-like signals not present in the DR25 TCE catalogue, including 46 monotransit candidates. Applied withoutretraining to 47 confirmed TESS planets in the PLATO LOPS2 field, EXOVEIL achieves 100% recovery, demonstrating zero-shot cross-mission transfer. At PLATO's 25-second cadence, detection reaches 100 ppm -- approaching the Earth-analog regime. I provide the first application of conformal prediction to transit detection (95.9% empirical coverage) and release the system as pip install exoveil with pretrained weights and a candidate catalogue.
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。