Transit spectroscopy is a powerful tool to decode the chemical composition of the atmospheres of extrasolar planets. In this paper we focus on unsupervised techniques for analyzing spectral data from transiting exoplanets. We demonstrate methods for i) cleaning and validating the data, ii) initial exploratory data analysis based on summary statistics (estimates of location and variability), iii) exploring and quantifying the existing correlations in the data, iv) pre-processing and linearly transforming the data to its principal components, v) dimensionality reduction and manifold learning, vi) clustering and anomaly detection, vii) visualization and interpretation of the data. To illustrate the proposed unsupervised methodology, we use a well-known public benchmark data set of synthetic transit spectra. We show that there is a high degree of correlation in the spectral data, which calls for appropriate low-dimensional representations. We explore a number of different techniques for such dimensionality reduction and identify several suitable options in terms of summary statistics, principal components, etc. We uncover interesting structures in the principal component basis, namely, well-defined branches corresponding to different chemical regimes of the underlying atmospheres. We demonstrate that those branches can be successfully recovered with a K-means clustering algorithm in fully unsupervised fashion. We advocate for a three-dimensional representation of the spectroscopic data in terms of the first three principal components, in order to reveal the existing structure in the data and quickly characterize the chemical class of a planet.
Postulating Exoplanetary Habitability via a Novel Anomaly Detection Method
BITS Pilani, K. K. Birla Goa Campus（印度博拉理工学院果阿分校）；CSIS and APPCAIR, BITS Pilani, K. K. Birla Goa Campus（印度博拉理工学院果阿分校CSIS与APPCAIR中心）；Indian Institute of Astrophysics（印度天体物理研究所）
Automated identification of transiting exoplanet candidates in NASA Transiting Exoplanets Survey Satellite (TESS) data with machine learning methods
Catholic University of America（美国天主教大学）；Tel Aviv University（特拉维夫大学）；ThetaRay（ThetaRay公司）
一种使用机器学习（ML）方法的新型人工智能（AI）技术结合了由ThetaRay，Inc.应用于NASA的凌日系外行星勘测卫星（TESS）数据集，以识别系外行星候选者。AI/ML ThetaRay系统最初使用开普勒系外行星数据进行训练，并在应用于TESS数据之前使用确认的系外行星进行验证。数据的现有和新特征基于各种观测参数，通过采用半监督和无监督机器学习技术构建并用于AI/ML分析。通过将ThetaRay系统应用于TESS任务产生的10，803个阈值交叉事件（TCEs）的光变曲线，该算法从Mikulski Archive for Space Telescopes获得，该算法产生了约50个目标以供进一步分析，我们通过进一步的人工审查发现了三个新的系外行星候选者。这项研究首次展示了将特定的基于AI/ML的方法成功应用于大型天体物理数据集，以快速自动分类TCE。
Machine-learning clustering of close-in exoplanet populations: links to pebble accretion
Center for Star and Planet Formation（星系与行星形成中心）；Globe Institute（全球研究所）；University of Copenhagen（哥本哈根大学）；Lund Observatory（隆德天文台）；Department of Physics（物理系）；Lund University（隆德大学）；Graduate Institute of Astronomy（天文研究所）；National Central University（国立中央大学）
University of Bridgeport（桥港大学）；University of the Potomac（波托马克大学）；Westcliff University（韦斯特克利夫大学）；Gannon University（甘农大学）；The University of Texas at Arlington（德克萨斯大学阿灵顿分校）；Washington University of Science and Technology（华盛顿科学技术大学）；Trine University（特莱恩大学）
Machine Learning as a Transformative Tool for (Exo-)Planetary Science
Institut of Space Research, German Aerospace Center (DLR)（德国航空航天中心空间研究所）；Division of Space Research and Planetary Sciences, Physics Institute, University of Bern（伯尔尼大学物理学院空间研究与行星科学系）；Center for Space and Habitability, University of Bern（伯尔尼大学太空与宜居性中心）；Southwest Research Institute（西南研究院）；ETH Zurich, Institute for Particle Physics and Astrophysics（苏黎世联邦理工学院粒子物理与天体物理研究所）
