.png){kind=icon}
.png){kind=icon}
Return
Transfer Learning with Gradient-Structural Regularization for Turbulent Combustion under Data Scarcity
.png){kind=icon}
OA
AI
Z
Y
M
Y
X
S
Z
W
DOI：10.1016/j.egyai.2026.100854.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A transfer learning framework with structural regularization predicts turbulent flames under data scarcity. • Gradient structural regularization preserves sharp flame fronts and shear layers, outperforming conventional data-driven models. • The model simultaneously predicts velocity, temperature, and key species distributions in three-dimensional turbulent combustion.
Keywords:
Turbulent combustion
Transfer learning
Gradient-structural regularization
Data scarcity
Multiphysics field prediction
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.6
Papers:
835
Citations:
3.1K