Unsupervised Learning for Stellar Spectra with Deep Normalizing Flows

Jo Ciuca, Yuan-Sen Ting

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    Abstract

    Stellar spectra encode detailed information about the stars. However, most machine learning approaches in stellar spectroscopy focus on supervised learning. We introduce Mendis, an unsupervised learning method, which adopts normalizing flows consisting of Neural Spline Flows and GLOW to describe the complex distribution of spectral space. A key advantage of Mendis is that we can describe the conditional distribution of spectra, conditioning on stellar parameters, to unveil the underlying structures of the spectra further. In particular, our study demonstrates that Mendis can robustly capture the pixel correlations in the spectra leading to the possibility of detecting unknown atomic transitions from stellar spectra. The probabilistic nature of Mendis also enables a rigorous determination of outliers in extensive spectroscopic surveys without the need to measure elemental abundances through existing analysis pipelines beforehand.
    Original languageEnglish
    Title of host publicationProceedings of ICML 2022
    EditorsKamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, Sivan
    Place of PublicationUnited States
    PublisherProceedings of Machine Learning Research
    Publication statusPublished - 2022
    Event39th International Conference on Machine Learning, ICML 2022 - Baltimore, Maryland, USA
    Duration: 1 Jan 2022 → …

    Conference

    Conference39th International Conference on Machine Learning, ICML 2022
    Period1/01/22 → …
    OtherJuly 17, 2022

    Fingerprint

    Dive into the research topics of 'Unsupervised Learning for Stellar Spectra with Deep Normalizing Flows'. Together they form a unique fingerprint.

    Cite this