Physics-Informed Deep Neural Operator Networks

Computational methods in engineering & the sciences, Journal Year: 2023, Volume and Issue: unknown, P. 219 - 254

Published: Jan. 1, 2023

Language: Английский

---

Learning Nonlinear Reduced Models from Data with Operator Inference

Annual Review of Fluid Mechanics, Journal Year: 2023, Volume and Issue: 56(1), P. 521 - 548

Published: Nov. 2, 2023

This review discusses Operator Inference, a nonintrusive reduced modeling approach that incorporates physical governing equations by defining structured polynomial form for the model, and then learns corresponding operators from simulated training data. The model of Inference is sufficiently expressive to cover wide range nonlinear dynamics found in fluid mechanics other fields science engineering, while still providing efficient computations. learning steps are rooted classical projection-based reduction; thus, some rich theory reduction can be applied models learned with Inference. connection offers pathway toward deriving error estimates gaining insights improve predictions. Furthermore, through formulations preserve Hamiltonian structures, important properties such as energy conservation guaranteed predictions beyond horizon. illustrates key computational large-scale combustion example.

Language: Английский

---

Neural-network-augmented projection-based model order reduction for mitigating the Kolmogorov barrier to reducibility

Journal of Computational Physics, Journal Year: 2023, Volume and Issue: 492, P. 112420 - 112420

Published: Aug. 10, 2023

Language: Английский

---

Generative reduced basis method

Computer Methods in Applied Mechanics and Engineering, Journal Year: 2025, Volume and Issue: 437, P. 117754 - 117754

Published: Jan. 30, 2025

Language: Английский

---

A Parallel Implementation of Reduced-Order Modeling of Large-Scale Systems

AIAA SCITECH 2022 Forum, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 3, 2025

Language: Английский

---

The role of interface boundary conditions and sampling strategies for Schwarz-based coupling of projection-based reduced order models

Journal of Computational and Applied Mathematics, Journal Year: 2025, Volume and Issue: unknown, P. 116584 - 116584

Published: Feb. 1, 2025

Language: Английский

---

SNF-ROM: Projection-based nonlinear reduced order modeling with smooth neural fields

Journal of Computational Physics, Journal Year: 2025, Volume and Issue: unknown, P. 113957 - 113957

Published: March 1, 2025

Language: Английский

---

Predictive reduced order modeling of chaotic multi-scale problems using adaptively sampled projections

Journal of Computational Physics, Journal Year: 2023, Volume and Issue: 491, P. 112356 - 112356

Published: July 13, 2023

Language: Английский

---

Symplectic model reduction of Hamiltonian systems using data-driven quadratic manifolds

Computer Methods in Applied Mechanics and Engineering, Journal Year: 2023, Volume and Issue: 417, P. 116402 - 116402

Published: Sept. 8, 2023

Language: Английский

---

Learning physics-based reduced-order models from data using nonlinear manifolds

Chaos An Interdisciplinary Journal of Nonlinear Science, Journal Year: 2024, Volume and Issue: 34(3)

Published: March 1, 2024

We present a novel method for learning reduced-order models of dynamical systems using nonlinear manifolds. First, we learn the manifold by identifying structure in data through general representation problem. The proposed approach is driven embeddings low-order polynomial form. A projection onto reveals algebraic reduced-space system that governs problem interest. matrix operators model are then inferred from operator inference. Numerical experiments on number problems demonstrate generalizability methodology and increase accuracy can be obtained over modeling methods employ linear subspace approximation.

Language: Английский

---