.png){kind=icon}
.png){kind=icon}
Return
Harnessing physics-informed operators for high-dimensional reliability analysis problems
.png){kind=icon}
PRE
AI
DOI：10.1016/j.probengmech.2025.103807.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Achieves 100% data efficiency by relying solely on governing physics for training. • Adeptly handles various inputs, including initial conditions, source functions, and parametric fields. • The method is scalable, enabling it to manage increasingly complex systems. • Proven to achieve high predictive accuracy in high-dimensional stochastic input fields.
Keywords:
physics-informed
data efficiency
scalable modeling
stochastic inputs
predictive accuracy
Journal
IF:
3.5
Papers:
1.7K
Citations:
4.1K