.png){kind=icon}
.png){kind=icon}
Return
Sequential domain decomposition physics-informed neural networks for forward and inverse problems of nonlinear partial differential equations
.png){kind=icon}
PRE
AI
Y
J
B
DOI：10.1016/j.physa.2026.131799.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A novel SDD-PINNs framework is proposed by combining temporal decomposition and dense information transfer. • Dense interior sampling replaces sparse interface-point propagation between subdomains. • The proposed transfer mechanism improves temporal consistency and long-time prediction accuracy. • Superior accuracy is demonstrated on several nonlinear wave equations compared with PINNs and TDD-PINNs.
Journal
P
IF:
3.1
Papers:
1.3K
Citations:
3.6W
Organization
No organization information available
Cited Papers