Explainable machine learning in materials science

X Zhong, B Gallagher, S Liu, B Kailkhura… - npj computational …, 2022 - nature.com
Abstract Machine learning models are increasingly used in materials studies because of
their exceptional accuracy. However, the most accurate machine learning models are …

Data-driven prediction in dynamical systems: recent developments

A Ghadami, BI Epureanu - Philosophical Transactions of …, 2022 - royalsocietypublishing.org
In recent years, we have witnessed a significant shift toward ever-more complex and ever-
larger-scale systems in the majority of the grand societal challenges tackled in applied …

Lasdi: Parametric latent space dynamics identification

WD Fries, X He, Y Choi - Computer Methods in Applied Mechanics and …, 2022 - Elsevier
Enabling fast and accurate physical simulations with data has become an important area of
computational physics to aid in inverse problems, design-optimization, uncertainty …

Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniques

T Kadeethum, F Ballarin, Y Choi, D O'Malley… - Advances in Water …, 2022 - Elsevier
Natural convection in porous media is a highly nonlinear multiphysical problem relevant to
many engineering applications (eg, the process of CO 2 sequestration). Here, we extend …

A fast and accurate domain decomposition nonlinear manifold reduced order model

AN Diaz, Y Choi, M Heinkenschloss - Computer Methods in Applied …, 2024 - Elsevier
This paper integrates nonlinear-manifold reduced order models (NM-ROMs) with domain
decomposition (DD). NM-ROMs approximate the full order model (FOM) state in a nonlinear …

Gplasdi: Gaussian process-based interpretable latent space dynamics identification through deep autoencoder

C Bonneville, Y Choi, D Ghosh, JL Belof - Computer Methods in Applied …, 2024 - Elsevier
Numerically solving partial differential equations (PDEs) can be challenging and
computationally expensive. This has led to the development of reduced-order models …

Reduced order models for Lagrangian hydrodynamics

DM Copeland, SW Cheung, K Huynh, Y Choi - Computer Methods in …, 2022 - Elsevier
As a mathematical model of high-speed flow and shock wave propagation in a complex
multimaterial setting, Lagrangian hydrodynamics is characterized by moving meshes …

Model reduction of convection-dominated partial differential equations via optimization-based implicit feature tracking

MA Mirhoseini, MJ Zahr - Journal of Computational Physics, 2023 - Elsevier
This work introduces a new approach to reduce the computational cost of solving partial
differential equations (PDEs) with convection-dominated solutions: model reduction with …

Component-wise reduced order model lattice-type structure design

S McBane, Y Choi - Computer methods in applied mechanics and …, 2021 - Elsevier
Lattice-type structures can provide a combination of stiffness with light weight that is
desirable in a variety of applications. Design optimization of these structures must rely on …

gLaSDI: Parametric physics-informed greedy latent space dynamics identification

X He, Y Choi, WD Fries, JL Belof, JS Chen - Journal of Computational …, 2023 - Elsevier
A parametric adaptive physics-informed greedy Latent Space Dynamics Identification
(gLaSDI) method is proposed for accurate, efficient, and robust data-driven reduced-order …