RAVEN: RAnking and Validation of ExoplaNets
Andreas Hadjigeorghiou, David J. Armstrong, Kaiming Cui, Marina Lafarga Magro, Luis Agustín Nieto, Rodrigo F. Díaz, Lauren Doyle, Vedad Kunovac
我们提出了RAVEN，一个为TESS系外行星候选者新开发的审查和验证流程。该流程采用贝叶斯框架，通过使用梯度提升决策树和高斯过程分类器，推导候选者相对于一组误报(FP)情景为行星的后验概率。这些分类器在综合的合成训练集上进行训练，包括模拟行星和注入TESS光变曲线的8种天体物理误报情景。这些训练集允许大规模候选者审查和针对个体误报情景的性能验证。还包括一个非模拟误报训练集，由主要由恒星变率和系统噪声引起的真实TESS候选者组成。机器学习推导的概率与情景特定的先验概率（包括候选者的位置概率）相结合，以计算最终的后验概率。行星后验概率大于99%的候选者...
We present RAVEN, a newly developed vetting and validation pipeline for TESS exoplanet candidates. The pipeline employs a Bayesian framework to derive the posterior probability of a candidate being a planet against a set of False Positive (FP) scenarios, through the use of a Gradient Boosted Decision Tree and a Gaussian Process classifier, trained on comprehensive synthetic training sets of simulated planets and 8 astrophysical FP scenarios injected into TESS lightcurves. These training sets all...
