About Me
|
I am a motivated scientific problem solver with interests in scientific machine learning and computational modeling.
Currently, I am a Postdoctoral Research Associate at Washington University in St. Louis with the Computational Cardiac Mechanics and AI Lab, where I am working on scientific machine learning for cardiovascular flow. I am developing uncertainty-aware and physics-informed machine learning methods for cardiovascular flow reconstruction from echocardiograms. The goal of this work is to enhance physical information obtained from medical imaging that can better inform patient-specific diagnosis and treatment planning. I earned my B.S. in mechanical engineering at UC Berkeley in 2019, where I studied aerodynamic shape optimization with deep learning in the CFD Lab. At Stanford University, I earned my M.S. in 2021 and my Ph.D. in 2025 under the advisement of Ali Mani. My Ph.D. dissertation was on turbulence modeling for Rayleigh-Taylor instability, and I also worked on forced turbulence simulations for tuning Reynolds Stress models. In my free time, I enjoy drawing, gardening, knitting, and 3D printing. |
Research
|
My research interests are in computational fluid dynamics and scientific machine learning.
My postdoctoral research focuses on machine learning methods for computational modeling of the heart.
My Ph. D. thesis focused on turbulence modeling for Rayleigh-Taylor instability using the Macroscopic Forcing Method.
For a full list of my publications, please see my Google Scholar. |
|
Echocardiography (echo) is a medical imaging technique that allows for real-time visualization of cardiac structures at the bedside.
Coupled with color Doppler, echo provides useful information about the hemodynamics in the heart that is commonly used by clinicians for diagnosis and treatment planning.
However, echo and Doppler images are often noisy and sparse, leading to substantial uncertainties in blood flow measurements.
This work aims to reconstruct full spatio-temporal flow fields in the heart from echo measurements using machine learning. We employ a diffusion-based probabilistic model to allow for uncertainty quantification of the flow predictions. Additionally, we enforce physical constraints to ensure the generated fields are consistent with not only the echo data but also the governing Navier-Stokes equations. |
|
Rayleigh-Taylor (RT) instability—when a light fluid is accelerated into a heavy fluid—can occur in inertial confinement fusion (ICF) and significantly reduce energy output.
Thus, it is important to accurately model RT mixing during the ICF experiment design process.
This work investigates the importance of non-locality in modeling turbulent RT mixing using the Macroscopic Forcing Method, a numerical approach to determine turbulent closure operators from high-fidelity simulations.
Related publications::
|
|
Physical data usually exist on irregular grids due to complex geometries encountered in real world problems.
In this work, we present the Deep Differentiable Shape Layer (DDSL), which leverages the non-uniform Fourier transform to facilitate deep learning on arbitrary geometries.
I derived the analytical derivative for the transform, to allow for fast backpropagation for neural network training as well as shape optimization after training.
I demonstrated the utility of the DDSL in the optimization of airfoil shapes for low lift-drag ratios.
Related publications::
|
3D Printing
|
|
|
Skills
The splash animation is of a triply-periodic forced turbulence simulation.
The frames traverse in the y-direction through x-z planes, and the color represents velocity magnitude.
I ran this simulation using a pseudo-spectral LES code.