Scientific machine learning through physics–informed neural networks: Where we are and what's next

S Cuomo, VS Di Cola, F Giampaolo, G Rozza… - Journal of Scientific …, 2022 - Springer
Abstract Physics-Informed Neural Networks (PINN) are neural networks (NNs) that encode
model equations, like Partial Differential Equations (PDE), as a component of the neural …

Physics-guided, physics-informed, and physics-encoded neural networks in scientific computing

SA Faroughi, N Pawar, C Fernandes, M Raissi… - arXiv preprint arXiv …, 2022 - arxiv.org
Recent breakthroughs in computing power have made it feasible to use machine learning
and deep learning to advance scientific computing in many fields, including fluid mechanics …

A comprehensive and fair comparison of two neural operators (with practical extensions) based on fair data

L Lu, X Meng, S Cai, Z Mao, S Goswami… - Computer Methods in …, 2022 - Elsevier
Neural operators can learn nonlinear mappings between function spaces and offer a new
simulation paradigm for real-time prediction of complex dynamics for realistic diverse …

Learning the solution operator of parametric partial differential equations with physics-informed DeepONets

S Wang, H Wang, P Perdikaris - Science advances, 2021 - science.org
Partial differential equations (PDEs) play a central role in the mathematical analysis and
modeling of complex dynamic processes across all corners of science and engineering …

A physics-informed variational DeepONet for predicting crack path in quasi-brittle materials

S Goswami, M Yin, Y Yu, GE Karniadakis - Computer Methods in Applied …, 2022 - Elsevier
Failure trajectories, probable failure zones, and damage indices are some of the key
quantities of relevance in brittle fracture mechanics. High-fidelity numerical solvers that …

On universal approximation and error bounds for Fourier neural operators

N Kovachki, S Lanthaler, S Mishra - Journal of Machine Learning Research, 2021 - jmlr.org
Fourier neural operators (FNOs) have recently been proposed as an effective framework for
learning operators that map between infinite-dimensional spaces. We prove that FNOs are …

Physics-informed machine learning: A survey on problems, methods and applications

Z Hao, S Liu, Y Zhang, C Ying, Y Feng, H Su… - arXiv preprint arXiv …, 2022 - arxiv.org
Recent advances of data-driven machine learning have revolutionized fields like computer
vision, reinforcement learning, and many scientific and engineering domains. In many real …

Reliable extrapolation of deep neural operators informed by physics or sparse observations

M Zhu, H Zhang, A Jiao, GE Karniadakis… - Computer Methods in …, 2023 - Elsevier
Deep neural operators can learn nonlinear mappings between infinite-dimensional function
spaces via deep neural networks. As promising surrogate solvers of partial differential …

Error estimates for deeponets: A deep learning framework in infinite dimensions

S Lanthaler, S Mishra… - … of Mathematics and Its …, 2022 - academic.oup.com
DeepONets have recently been proposed as a framework for learning nonlinear operators
mapping between infinite-dimensional Banach spaces. We analyze DeepONets and prove …

Model reduction and neural networks for parametric PDEs

K Bhattacharya, B Hosseini, NB Kovachki… - The SMAI journal of …, 2021 - numdam.org
We develop a general framework for data-driven approximation of input-output maps
between infinitedimensional spaces. The proposed approach is motivated by the recent …