.png){kind=icon}
.png){kind=icon}
Return
What do physics-informed DeepONets learn? Understanding and improving training for scientific computing applications
.png){kind=icon}
OA
AI
E
A
S
B
P
DOI：10.1016/j.jcp.2026.114851.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Physics-informed deep operator networks (DeepONets) have emerged as a promising approach toward numerically approximating the solution of partial differential equations (PDEs), without requiring simulation data to train. In this work, we aim to develop further understanding of what is being learned by physics-informed DeepONets by assessing the universality of the extracted basis functions and demonstrating their potential toward model reduction with spectral methods. Results provide clarity about measuring the performance of a physics-informed DeepONet through the decays of singular values and expansion coefficients. In addition, we propose a transfer learning approach for improving training for physics-informed DeepONets between parameters of the same PDE as well as across different, but related, PDEs where these models struggle to train well. This approach results in significant error reduction and learned basis functions that are more effective in representing the solution of a PDE.
Keywords:
Deep operator networks
Physics-informed operator learning
Model reduction
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.8
Papers:
1.5W
Citations:
7.4W
Organization
Cited Papers