.png){kind=icon}
.png){kind=icon}
Return
Physics-embedded graph neural operator for interaction-controlled colloidal aggregation
.png){kind=icon}
OA
AI
DOI：10.1016/j.watres.2026.125773.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Graph neural operator surrogates population balance equations with R2 > 0.99 across ionic strength, zeta potential, particle size, and concentration ranges. • Embedding Brownian transport in graph edges achieves significant computational efficiency versus physics-informed loss while maintaining superior prediction accuracy. • Attention analysis reveals model learned XDLVO-controlled regime transitions, accurately capturing collision efficiency and frequency competition effects.
Keywords:
Colloidal aggregation
Population balance equation
Graph neural operator
Surrogate modeling
XDLVO theory
Attention mechanism
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
12.4
Papers:
3.1W
Citations:
15.7W