NALGMar 6, 2024

TGPT-PINN: Nonlinear model reduction with transformed GPT-PINNs

arXiv:2403.03459v116 citationsh-index: 26Comput Method Appl Mech Eng
Originality Highly original
AI Analysis

This addresses model reduction challenges in transport-dominated PDEs for computational physics and engineering, representing a novel paradigm rather than an incremental improvement.

The paper tackled nonlinear model order reduction for transport-dominated partial differential equations with parameter-dependent discontinuities, introducing TGPT-PINN, which incorporates a shock-capturing loss and transform layer to overcome linear reduction limitations, demonstrating effectiveness on nontrivial parametric PDEs.

We introduce the Transformed Generative Pre-Trained Physics-Informed Neural Networks (TGPT-PINN) for accomplishing nonlinear model order reduction (MOR) of transport-dominated partial differential equations in an MOR-integrating PINNs framework. Building on the recent development of the GPT-PINN that is a network-of-networks design achieving snapshot-based model reduction, we design and test a novel paradigm for nonlinear model reduction that can effectively tackle problems with parameter-dependent discontinuities. Through incorporation of a shock-capturing loss function component as well as a parameter-dependent transform layer, the TGPT-PINN overcomes the limitations of linear model reduction in the transport-dominated regime. We demonstrate this new capability for nonlinear model reduction in the PINNs framework by several nontrivial parametric partial differential equations.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes