arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.12872astro-ph.EPastro-ph.IMastro-ph.SRcs.LG
收藏

一种利用物理观测量校正视向速度的机器学习方法

A Machine Learning approach for correcting radial velocities using physical observables

Institut de Ciències de l’Espai (ICE, CSIC)(空间科学研究所(西班牙国家研究委员会));Institut d’Estudis Espacials de Catalunya (IEEC)(加泰罗尼亚空间研究所);University of Warwick(华威大学);Instituto de Astrofísica de Andalucía (IAA-CSIC)(安达卢西亚天体物理研究所(西班牙国家研究委员会));The Open University(开放大学);Max Planck Institut für Sonnensystemforschung (MPS)(马克斯·普朗克太阳系研究所);Zentrum für Astronomie der Universität Heidelberg(海德堡大学天文中心);Georg-August-Universität Göttingen(哥廷根大学)

M. Perger, G. Anglada-Escudé, D. Baroch, M. Lafarga, I. Ribas, J. C. Morales, E. Herrero, P. J. Amado, J. R. Barnes, J. A. Caballero, S. V. Jeffers, A. Quirrenbach, A. Reiners

AI总结:

本文提出用深度神经网络结合谱线轮廓参数和多波段测光等物理观测量校正恒星活动引起的视向速度变化,并在模拟和真实数据上验证了其有效性。

摘要:

高精度视向速度(RV)测量仍然是探测和表征系外行星的关键工具。虽然仪器精度持续提高,但恒星活动仍然是获得低于1-2 m/s精度的可靠测量的障碍。利用模拟和真实数据,我们研究了深度神经网络方法产生无活动影响的恒星多普勒测量的能力。作为案例研究,我们使用两颗已知恒星(波江座ε和显微镜座AU)的观测数据,两者都具有明显的活动引起的RV变化信号。使用starsim代码生成可观测量的合成数据(输入)和由此产生的RV信号(标签),并用于训练深度神经网络算法。我们确定了一种由卷积层和全连接层组成的架构,该架构适用于该任务。研究的指数包括平均谱线轮廓参数(宽度、二分线、对比度)和多波段测光。我们证明,这种与RV无关的方法可以大幅减少由已知物理效应(如黑子、自转和对流蓝移)引起的虚假多普勒变化。我们确定了具有最强预测能力的活动指数组合。当应用于真实观测时,我们观察到校正结果与观测到的变化有良好的匹配,但我们也发现噪声降低不如模拟中那样好,这可能是由于模拟物理缺乏细节所致。我们证明,对于已知的物理效应,模型驱动的机器学习方法足以清除活动引起的多普勒信号变化。有数十种已知的活动相关观测量,其反演能力尚未被探索,这表明使用额外的指标、更完整的模型以及采用优化采样策略的更多观测可以显著提升我们的去趋势能力。

英文摘要:

Precision radial velocity (RV) measurements continue to be a key tool to detect and characterise extrasolar planets. While instrumental precision keeps improving, stellar activity remains a barrier to obtain reliable measurements below 1-2 m/s accuracy. Using simulations and real data, we investigate the capabilities of a Deep Neural Network approach to produce activity free Doppler measurements of stars. As case studies we use observations of two known stars (Eps Eridani and AUMicroscopii), both with clear signals of activity induced RV variability. Synthetic data using the starsim code are generated for the observables (inputs) and the resulting RV signal (labels), and used to train a Deep Neural Network algorithm. We identify an architecture consisting of convolutional and fully connected layers that is adequate to the task. The indices investigated are mean line-profile parameters (width, bisector, contrast) and multi-band photometry. We demonstrate that the RV-independent approach can drastically reduce spurious Doppler variability from known physical effects such as spots, rotation and convective blueshift. We identify the combinations of activity indices with most predictive power. When applied to real observations, we observe a good match of the correction with the observed variability, but we also find that the noise reduction is not as good as in the simulations, probably due to the lack of detail in the simulated physics. We demonstrate that a model-driven machine learning approach is sufficient to clean Doppler signals from activity induced variability for well known physical effects. There are dozens of known activity related observables whose inversion power remains unexplored indicating that the use of additional indicators, more complete models, and more observations with optimised sampling strategies can lead to significant improvements in our detrending capabilities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑