Postdoctoral Fellow, InnoCORE PRISM-AI Center,
Korea Advanced Institute of Science & Technology (KAIST)
Affiliated Researcher, School of Civil and Environmental Engineering,
Georgia Institute of Technology
yj.choi@kaist.ac.kr | +82 10-5153-9271
I received my Ph.D. in civil engineering at the University of Texas at Austin with the thesis titled "Forward and Inverse Modeling of Granular Flows Using Differentiable Graph Neural Network Simulator". My current role is a Postdoctoral Fellow in the InnoCORE PRISM-AI Center at KAIST. I am also an Affiliated Researcher continuing collaborative work with the Geosystems Engineering group at the Georgia Institute of Technology.
My research focuses on AI-enhanced simulation, modeling, and automation for natural hazards, leveraging scientific machine learning (SciML), numerical simulation, computer vision, and high-performance computing. Specifically, I am actively using graph neural networks (GNNs) to learn to simulate complex soil interactions and fluid flows in an accurate, fast, and generalizable way, for solving forward and inverse problems, and for material property extraction. In addition, I explore AI-driven automation techniques for infrastructure health monitoring.
More details about my current and past research can be found here.