67 citations · 137 across the 6 of their papers we have counts for
4 papers · 1 filter
Deep Convolutional Ritz Method: Parametric PDE surrogates without labeled data
Jan Niklas Fuhg, Arnav Karmarkar, Teeratorn Kadeethum +2
Parametric surrogate models for partial differential equations (PDEs) are a necessary component for many applications in the computational sciences, and convolutional neural networ…
Reduced order modeling for flow and transport problems with Barlow Twins self-supervised learning
Teeratorn Kadeethum, Francesco Ballarin, Daniel O'Malley +3
We propose a unified data-driven reduced order model (ROM) that bridges the performance gap between linear and nonlinear manifold approaches. Deep learning ROM (DL-ROM) using deep-…
Continuous conditional generative adversarial networks for data-driven solutions of poroelasticity with heterogeneous material properties
T. Kadeethum, D. O'Malley, Y. Choi +3
Machine learning-based data-driven modeling can allow computationally efficient time-dependent solutions of PDEs, such as those that describe subsurface multiphysical problems. In…
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 +3
Natural convection in porous media is a highly nonlinear multiphysical problem relevant to many engineering applications (e.g., the process of sequestration). Here,…