Senior Project Advisor
Star formation, young stars, machine learning
Stellar ages can act as a marker of birth cluster membership for young stellar objects (YSOs), which allows for an improved understanding of the history of star formation in the solar neighborhood. However, the ages of YSOs have historically been difficult to predict on a large scale. Here, we develop a system of convolution neural network models to differentiate between YSOs and their more-evolved counterparts and predict YSO ages using Gaia and 2MASS photometry. The full model and resulting catalog recovers the properties of well-studied young stellar populations to a distance of five kiloparsecs, with significantly higher sensitivity within one kiloparsec, while also identifying new YSO candidate stars. We then explore the resulting catalog's implications for solar neighborhood star formation, and identify several large-scale structures, including two interesting ring or bubble-shaped groupings of young stars which may suggest radially triggered star forming events. Our results support the existence of an inclined Gould's Belt of local star formation, which may coincide with the Local Bubble. In addition, we also identify 26 high velocity 'runaway' stars from the Orion Nebula Cluster and characterize their likely origins.
McBride, Aidan; Lingg, Ryan; Kounkel, Marina; Covey, Kevin; and Hutchinson, Brian, "A Neural Network Approach to Identifying YSOs and Exploring Solar Neighborhood Star-Forming History" (2021). WWU Honors Program Senior Projects. 471.
Subjects - Topical (LCSH)
Stars--Formation; Neural networks (Computer science); Stars--Populations
Subjects - Names (LCNAF)
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.