paper-with-me

Papers

Multifidelity domain decomposition-based physics-informed neural networks and operators for time-dependent problems

2024-01-15 · Alexander Heinlein, Amanda A. Howard, Damien Beecroft, Panos Stinis

Multiscale problems are challenging for neural network-based discretizations of differential equations, such as physics-informed neural networks (PINNs). This can be (partly) attributed to the so-called spectral bias of neural networks. To improve the performance of PINNs for time-dependent problems, a combination of multifidelity stacking PINNs and domain decomposition-based finite basis PINNs is employed. In particular, to learn the high-fidelity part of the multifidelity model, a domain decomposition in time is employed. The performance is investigated for a pendulum and a two-frequency problem as well as the Allen-Cahn equation. It can be observed that the domain decomposition approach clearly improves the PINN and stacking PINN approaches. Finally, it is demonstrated that the FBPINN approach can be extended to multifidelity physics-informed deep operator networks.

📄 PDF Abstract BibTeX arXiv:2401.07888

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multifidelity Ensemble Kalman Filtering Using Surrogate Models Defined by Physics-Informed Autoencoders

2021-02-25 · Andrey A Popov, Adrian Sandu

Data assimilation is a Bayesian inference process that obtains an enhanced understanding of a physical system of interest by fusing information from an inexact physics-based model, and from noisy sparse observations of r…

Bayesian InferenceComputational Efficiency

Physics-Informed CoKriging: A Gaussian-Process-Regression-Based Multifidelity Method for Data-Model Convergence

2018-11-24 · Xiu Yang, David Barajas-Solano, Guzel Tartakovsky, Alexandre Tartakovsky

In this work, we propose a new Gaussian process regression (GPR)-based multifidelity method: physics-informed CoKriging (CoPhIK). In CoKriging-based multifidelity methods, the quantities of interest are modeled as linear…

Active LearningGaussian ProcessesGPRregression

Multifidelity Deep Operator Networks For Data-Driven and Physics-Informed Problems

2022-04-19 · Amanda A. Howard, Mauro Perego, George E. Karniadakis, Panos Stinis

Operator learning for complex nonlinear systems is increasingly common in modeling multi-physics and multi-scale systems. However, training such high-dimensional operators requires a large amount of expensive, high-fidel…

Operator learning

FB-HyDON: Parameter-Efficient Physics-Informed Operator Learning of Complex PDEs via Hypernetwork and Finite Basis Domain Decomposition

2024-09-13 · Milad Ramezankhani, Rishi Yash Parekh, Anirudh Deodhar, Dagnachew Birru

Deep operator networks (DeepONet) and neural operators have gained significant attention for their ability to map infinite-dimensional function spaces and perform zero-shot super-resolution. However, these models often r…

Operator learningSuper-Resolution

Scalable algorithms for physics-informed neural and graph networks

2022-05-16 · Khemraj Shukla, Mengjia Xu, Nathaniel Trask, George Em Karniadakis

Physics-informed machine learning (PIML) has emerged as a promising new approach for simulating complex physical and biological systems that are governed by complex multiscale processes for which some data are also avail…

BIG-bench Machine LearningPhysics-informed machine learning