Advancing Machine Learning for Stellar Activity and Exoplanet Period Rotation
Leiden Institute of Advanced Computer Science (LIACS), Leiden University(莱顿大学高级计算机科学研究所(LIACS));Leiden Observatory, Leiden University(莱顿大学莱顿天文台);LUNEX;Eurospacehub-Green academy(欧洲太空枢纽绿色学院);ESA BIC(欧洲空间局商业创新中心);Directorate of Science, European Space Research and Technology Center (ESA-ESTEC)(欧洲空间研究与技术中心科学总局(ESA-ESTEC))
Fatemeh Fazel Hesar, Bernard Foing, Ana M. Heras, Mojtaba Raouf, Victoria Foing, Shima Javanmardi, Fons J. Verbeek
备注:
15 pages, 8 figures. Submitted for publication in A&A
This study applied machine learning models to estimate stellar rotation periods from corrected light curve data obtained by the NASA Kepler mission. Traditional methods often struggle to estimate rotation periods accurately due to noise and variability in the light curve data. The workflow involved using initial period estimates from the LS-Periodogram and Transit Least Squares techniques, followed by splitting the data into training, validation, and testing sets. We employed several machine learning algorithms, including Decision Tree, Random Forest, K-Nearest Neighbors, and Gradient Boosting, and also utilized a Voting Ensemble approach to improve prediction accuracy and robustness.
The analysis included data from multiple Kepler IDs, providing detailed metrics on orbital periods and planet radii. Performance evaluation showed that the Voting Ensemble model yielded the most accurate results, with an RMSE approximately 50\% lower than the Decision Tree model and 17\% better than the K-Nearest Neighbors model. The Random Forest model performed comparably to the Voting Ensemble, indicating high accuracy. In contrast, the Gradient Boosting model exhibited a worse RMSE compared to the other approaches. Comparisons of the predicted rotation periods to the photometric reference periods showed close alignment, suggesting the machine learning models achieved high prediction accuracy. The results indicate that machine learning, particularly ensemble methods, can effectively solve the problem of accurately estimating stellar rotation periods, with significant implications for advancing the study of exoplanets and stellar astrophysics.
The role of the Hubble Space Telescope in advancing our understanding of atmospheric escape in exoplanets
Space Telescope Science Institute(太空望远镜科学研究所);Johns Hopkins University(约翰斯·霍普金斯大学);Johns Hopkins Applied Physics Laboratory(约翰斯·霍普金斯大学应用物理实验室);University of Colorado Boulder(科罗拉多大学博尔德分校);University of Hawai’i at Mānoa(夏威夷大学马诺阿分校);Université Paris-Saclay(巴黎萨克雷大学);Université Paris Cité(巴黎西岱大学);CEA(法国原子能和替代能源委员会);CNRS(法国国家科学研究中心);Eureka Scientific, Inc.(尤里卡科学公司);NASA Goddard Space Flight Center(美国宇航局戈达德太空飞行中心);Kiel University(基尔大学);Istanbul Health and Technology University(伊斯坦布尔卫生与技术大学);University of Chicago(芝加哥大学);Arizona State University(亚利桑那州立大学);University of Arizona(亚利桑那大学);Wesleyan University(卫斯理安大学);Cornell University(康奈尔大学)
Identifying Exoplanets with Deep Learning. IV. Removing Stellar Activity Signals from Radial Velocity Measurements Using Neural Networks
Massachusetts Institute of Technology(麻省理工学院);University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);Université de Genève(日内瓦大学);Observatoire de Genève(日内瓦天文台);University of St Andrews(圣安德鲁斯大学);Facebook(脸书);Technical University of Denmark(丹麦技术大学);DTU Space, National Space Institute(丹麦技术大学国家空间研究所)
精确径向速度(RV)观测的系外行星探测目前受到恒星活动引入的虚假RV信号的限制。我们表明,线性回归和神经网络等机器学习技术可以有效地从RV观测中去除活动信号(由于星点/光斑)。以前的努力集中在使用高斯过程回归等建模技术及时仔细过滤活动信号(例如Haywood等人2014)。相反,我们系统地去除活动信号,只使用谱线的平均形状的变化,而没有关于何时收集观测结果的信息。我们在模拟数据(使用SOAP 2.0软件生成; Dumusque et al. 2014)和HARPS-N太阳望远镜对太阳的观测(Dumusque et al. 2015; Phillips et al. 2016; Collier Cameron et al. 2019)上训练了我们的机器学习模型。我们发现,这些技术可以预测和删除模拟数据(改善RV散射从82厘米/秒到3厘米/秒)和超过600个实际观测采取了近三年的HARPS-N太阳望远镜(改善RV散射从1.753米/秒到1.039米/秒,约1.7改善的一个因素)。在未来,这些或类似的技术可以从我们太阳系以外的恒星观测中去除活动信号,并最终帮助探测类太阳恒星周围的可居住区地球质量的系外行星。
Identifying Exoplanets with Deep Learning VI. Enhancing neural network mitigation of stellar activity RV signals with additional metrics
Imperial College London(帝国理工学院);Massachusetts Institute of Technology(麻省理工学院);University of Birmingham(伯明翰大学);Technical University of Denmark(丹麦技术大学);University of St Andrews(圣安德鲁斯大学);Fundación Galileo Galilei—INAF(伽利略基金会-INAF);Observatoire de Genève, Université de Genève(日内瓦天文台,日内瓦大学)
Magnetic activity in cool stars: manifestations and relevance to exoplanets
Max-Planck-Institut für Sonnensystemforschung(马克斯·普朗克太阳系统研究所);Centro de Rádio Astronomia e Astrofísica Mackenzie, Universidade Presbiteriana Mackenzie(麦肯齐射电天文学与天体物理学中心,麦肯齐长老会大学);Université Paris-Saclay, Université Paris Cité, CEA, CNRS, AIM(巴黎萨克雷大学,巴黎西岱大学,法国原子能和替代能源委员会,法国国家科学研究中心,天文信息与管理实验室);Leibniz-Institut für Astrophysik Potsdam (AIP)(波茨坦莱布尼茨天体物理研究所);HUN-REN Research Centre for Astronomy and Earth Sciences, Konkoly Observatory(匈牙利研究网络地球与天文学研究中心,孔科利天文台);Instituto de Astronomía y Física del Espacio (IAFE, UBA-CONICET)(空间天体物理学与天体物理研究所);The Catholic University of America(美国天主教大学);The Hakubi Center for Advanced Research, Kyoto University(京都大学博雅教育研究中心);Department of Physics, Kyoto University(京都大学物理学系);University of Helsinki(赫尔辛基大学)
Infrared Flares from M Dwarfs: a Hinderance to Future Transiting Exoplanet Studies
许多当前和未来的系外行星任务正在推动红外(IR)波长,行星和恒星之间的通量对比更有利(Deming et al. 2009),恒星磁活动的影响减少。事实上,最近对恒星黑子和光斑的分析发现,这些形式的恒星活动不会对具有JWST的FGKM恒星的凌日特征或科学潜力产生实质性影响(Zellem et al. 2017)。然而,在耀斑的情况下,这是不正确的,我证明这可能是一个障碍,过境研究在这份说明。
Young M dwarfs flare activity model: Towards better exoplanetary atmospheric characterisation
University of Oslo(奥斯陆大学);National Solar Observatory, University of Colorado Boulder(美国国家太阳天文台,科罗拉多大学博尔德分校);Department of Astrophysical and Planetary Sciences, University of Colorado(科罗拉多大学天体物理与行星科学系);Laboratory for Atmospheric and Space Physics, University of Colorado Boulder(科罗拉多大学博尔德分校大气与空间物理实验室);Rosseland Centre for Solar Physics, University of Oslo(奥斯陆大学罗斯兰太阳物理中心);Institute of Theoretical Astrophysics, University of Oslo(奥斯陆大学理论天体物理研究所)
The CARMENES search for exoplanets around M dwarfs. Radial velocities and activity indicators from cross-correlation functions with weighted binary masks
HWO Target Stars and Systems: Activity and Rotation Catalog (ARC) of Potential Target Stars for the Habitable Worlds Observatory
University of California, Riverside(加州大学河滨分校);National Optical-Infrared Astronomy Research Laboratory(国家光学红外天文研究实验室);Dartmouth College(达特茅斯学院);Instituto de Astronomía y Física del Espacio (IAFE, CONICET-UBA)(太空天体物理学与天文学研究所 (IAFE, 阿根廷国家科学研究委员会-布宜诺斯艾利斯大学));Universidad de Buenos Aires(布宜诺斯艾利斯大学);Jet Propulsion Laboratory, California Institute of Technology(加州理工学院喷气推进实验室);Centro de Astrobiología, CSIC-INTA(西班牙国家航空航天技术研究所-西班牙国家研究委员会天体生物学中心);Georgia State University(佐治亚州立大学);RECONS Institute(RECONS研究所);UNTREF(特立尼达德大学)
The effects of stellar activity on optical high-resolution exoplanet transmission spectra
色球敏感的原子线显示不同的光谱在恒星活动区,斑点,和光球,提高的可能性,系外行星传输光谱被污染的恒星盘的各个部分之间的对比。为了探索这种效应,我们对G型和K型恒星进行了凌日模拟,其谱线分别为Ca II K 3933、Na I 5890、H I 6563(H $α$)和He I 10830。我们发现,强的光斑发射和大的覆盖率可以贡献一个不可忽略的量的透射光谱,特别是对于H $α$,钙II K,和钠I D,而斑点和细丝是相对不重要的。污染的量强烈地依赖于有源区的位置和本征发射强度。特别地,活动区域必须沿着运输弦集中,以便产生一致的运输中信号。例如,在活跃纬度的凌日过程中,Na I和H $α$的平均吸收特征可以分别达到$\approx 0.2\%$和$0.3\%$,其线发射强度与中等强度的太阳耀斑相似。像HD 189733这样经过活跃恒星的行星,其透射光谱很可能受到对比度效应的影响,尽管活动区几何形状和发射强度的严格限制使得一致的过境特征不太可能完全归因于对比度效应。He I 10830的影响并不强烈,吸收信号可能被恒星活动稀释,而不是增强。因此,He I 10830应该被认为是探测扩展大气层的优先目标,即使是在活跃恒星的情况下。
Insights into the Exoplanet Radius Valley from Host-Star Ages, Activity, Chemistry, and Birth Radius
School of Science, Hangzhou Dianzi University(杭州电子科技大学理学院);National Astronomical Data Center Zhijiang Branch(国家天文台紫江分中心);CAS Key Laboratory of Optical Astronomy, National Astronomical Observatories, Chinese Academy of Sciences(中国科学院国家天文台光学天文重点实验室);Department of Astronomy, The Ohio State University(俄亥俄州立大学天文学系);Center for Cosmology and Astroparticle Physics (CCAPP), The Ohio State University(俄亥俄州立大学宇宙学与高能粒子物理中心);School of Physics and Astronomy, Beijing Normal University(北京师范大学物理与天文学院);School of Science, Xichang University(西昌学院理学院)
Analysis of Habitability and Stellar Habitable Zones from Observed Exoplanets
Jet Propulsion Laboratory, California Institute of Technology(加州理工学院喷气推进实验室);Lakeside School(湖畔学校);Pacific Academy(太平洋学院);Burke Institute for Theoretical Physics, California Institute of Technology(加州理工学院伯克理论物理研究所)