Research
Research interests include stellar abundances, Galactic evolution, spectroscopic surveys, Gaia-based dynamics, and deep learning applications for large astronomical data sets.
Theme 01
This work develops deep-learning approaches to identify ex-situ stars using 6D kinematics and actions from Gaia DR3.
The analysis maps ex-situ star distributions in radial and vertical directions and estimates their proportions within the Galactic disk and halo.
Theme 02
This work studies a rotating stellar component in the bulge and halo through neural-network classification applied to Gaia DR3.
Test-particle simulations with an axisymmetric background potential and a decelerating central bar are used to interpret angular-momentum transfer mechanisms.
Theme 03
Neural-network models are used to estimate stellar parameters and elemental abundances from low-resolution LAMOST DR8 spectra for 1.2 million giants.
The resulting value-added catalog supports investigations of the Milky Way's chemical evolution.
Theme 04
Neural networks and deep learning are core methods for classification and stellar-parameter inference from large astronomical surveys.
Additional professional activity includes participation in meetings or schools related to astrostatistics, machine learning, data visualization, and AI-driven discovery in physics and astrophysics.