.png){kind=icon}
Return
Separated-variable physics informed neural operators for solving dynamic PDEs
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ymssp.2026.114195.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A new SV-PINO framework solves spatiotemporal PDEs using variable separation and neural operators. • The method overcomes spectral bias in high-frequency problems via eigenfunction and wavelet decomposition. • The method simplifies high-order PDEs and complex boundaries into low-order ODEs for stable solving. • SV-PINO extends to discrete systems without explicit PDE forms, demonstrating strong generalization. • The framework outperforms existing methods in accuracy and robustness across diverse benchmark problems.
Keywords:
SV-PINO
spatiotemporal PDEs
neural operators
variable separation
spectral bias
Journal
IF:
8.9
Papers:
1.3W
Citations:
6.6W
Organization
Cited Papers
No cited papers available