Predicting Young Stellar Ages with Deep Learning
Research Mentor(s)
Hutchinson, Brian
Description
Studying the environments of star forming regions is critical to our understanding of early stellar evolution, but historically, observationally distinguishing clustered young stars from evolved field stars has been difficult. The ESA’s Gaia telescope allows for vastly improved cluster membership constraints through spatial and kinematical groupings, but this method fails for gravitationally ejected or high velocity members. Stellar ages, which can be extrapolated on an individual basis from photometric measurements, are a more general alternative to astrometric clustering in identifying cluster membership. We present a deep learning method using Gaia and 2MASS photometry to predict stellar ages for the pre-main-sequence branch. Our model, consisting of two cascading neural networks, is trained to recognize young stars and stellar ages derived from the cluster isochrone fitting of nearby star forming regions. After classifying the evolutionary stage of input stars, the model predicts ages for all sources categorized as pre-main-sequence. Our model successfully recovers known nearby star forming regions while identifying additional candidate members from the Gaia catalog, and shows promise for use in studying extreme stellar kinematics in these regions.
Document Type
Event
Start Date
18-5-2020 12:00 AM
End Date
22-5-2020 12:00 AM
Department
Computer Science
Genre/Form
student projects, posters
Subjects – Topical (LCSH)
Stars--Formation; Planetary science; Deep learning (Machine learning)
Type
Image
Rights
Copying of this document in whole or in part is allowable only for scholarly purposes. It is understood, however, that any copying or publication of this document for commercial purposes, or for financial gain, shall not be allowed without the author’s written permission.
Language
English
Format
application/pdf
Predicting Young Stellar Ages with Deep Learning
Studying the environments of star forming regions is critical to our understanding of early stellar evolution, but historically, observationally distinguishing clustered young stars from evolved field stars has been difficult. The ESA’s Gaia telescope allows for vastly improved cluster membership constraints through spatial and kinematical groupings, but this method fails for gravitationally ejected or high velocity members. Stellar ages, which can be extrapolated on an individual basis from photometric measurements, are a more general alternative to astrometric clustering in identifying cluster membership. We present a deep learning method using Gaia and 2MASS photometry to predict stellar ages for the pre-main-sequence branch. Our model, consisting of two cascading neural networks, is trained to recognize young stars and stellar ages derived from the cluster isochrone fitting of nearby star forming regions. After classifying the evolutionary stage of input stars, the model predicts ages for all sources categorized as pre-main-sequence. Our model successfully recovers known nearby star forming regions while identifying additional candidate members from the Gaia catalog, and shows promise for use in studying extreme stellar kinematics in these regions.