On latent dynamics learning in nonlinear reduced order modeling

N Farenga, S Fresca, S Brivio, A Manzoni - Neural Networks, 2025 - Elsevier
In this work, we present the novel mathematical framework of latent dynamics models
(LDMs) for reduced order modeling of parameterized nonlinear time-dependent PDEs. Our …

Physics‐Informed Active Learning With Simultaneous Weak‐Form Latent Space Dynamics Identification

X He, A Tran, DM Bortz, Y Choi - International Journal for …, 2025 - Wiley Online Library
The parametric greedy latent space dynamics identification (gLaSDI) framework has
demonstrated promising potential for accurate and efficient modeling of high‐dimensional …

Accelerating phase field simulations through a hybrid adaptive Fourier neural operator with U-net backbone

C Bonneville, N Bieberdorf, A Hegde, M Asta… - npj Computational …, 2025 - nature.com
Prolonged contact between a corrosive liquid and metal alloys can cause progressive
dealloying. For one such process as liquid-metal dealloying (LMD), phase field models have …

An Augmented Lagrangian Trust‐Region Method With Inexact Gradient Evaluations to Accelerate Constrained Optimization Problems Using Model Hyperreduction

T Wen, MJ Zahr - … Journal for Numerical Methods in Fluids, 2024 - Wiley Online Library
We present an augmented Lagrangian trust‐region method to efficiently solve constrained
optimization problems governed by large‐scale nonlinear systems with application to partial …

[HTML][HTML] Sparsified time-dependent Fourier neural operators for fusion simulations

MM Rahman, Z Bai, JR King, CR Sovinec, X Wei… - Physics of …, 2024 - pubs.aip.org
This paper presents a sparsified Fourier neural operator for coupled time-dependent partial
differential equations (ST-FNO) as an efficient machine learning surrogate for fluid and …

Sparse -Autoencoders for Scientific Data Compression

M Chung, R Archibald, P Atzberger… - arxiv preprint arxiv …, 2024 - arxiv.org
Scientific datasets present unique challenges for machine learning-driven compression
methods, including more stringent requirements on accuracy and mitigation of potential …

[PDF][PDF] WgLaSDI: Weak-Form Greedy Latent Space Dynamics Identification

X Hea, A Tranb, DM Bortzb, Y Choic - arxiv preprint arxiv …, 2024 - researchgate.net
The parametric greedy latent space dynamics identification (gLaSDI) framework has
demonstrated promising potential for accurate and efficient modeling of high-dimensional …