Research

AI4Science and Physis-informed Machine Learning

• Design and implement artificial intelligence models for science with governing laws integrated within its architecture
• Lead efforts on AI modeling of multi-scale, multi-phase, and multi-physics reactive and turbulent systems
• Generate and manage multiple terabyte-scale simulation datasets on HPC clusters
• Contribute to federal research proposals and mentor graduate/undergraduate researchers

Led or involved in the following projects:

• Unified Reactive Material Model for Meta-learning of Reactive Dynamics
• Multi-phase Flow Modeling with Physics-Aware Recurrent Convolutional Neural Network
• Physics-Aware Recurrent Convolutional Neural Network for Turbulence Flow
• Dynamics of Reactive Materials under Low, Modest and Strong Shock Loading
• Development of Physics-Aware Recurrent Convolutional Neural Network
• Accelerating Spin Dynamics Numerical Simulation with Physics-Aware Neural Network

Galactic Dynmaics and Data-driven Modeling

• Bridged data-driven models and physical first-principles for astrophysical, quantum mechanical and fluid systems
• Integrated data analysis pipelines across Gaia, APOGEE, and other large astronomical databases

Led or involved in the following projects:

• Searching for White Dwarf Main Sequence (WDMS) Binary Systems with Deep Learning
• Evolution of Magellanic Clouds through Stellar Kinematics and Chemistry with Gaia and APOGEE
• Evolution of the Milky Way Galaxy through Stellar Chemo-Kinematics Studies with Gaia and APOGEE
• Searching for Galaxy-galaxy Strong Gravitational Lensing in BOSS