.png){kind=icon}
.png){kind=icon}
Return
A multiscale Bayesian optimization framework for process and material codesign
.png){kind=icon}
OA
AI
DOI：10.1002/aic.70228.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The simultaneous design of processes and enabling materials such as solvents, catalysts, and adsorbents is challenging because molecular- and process-level decisions are strongly interdependent. Sequential approaches often yield suboptimal results since improvements in material properties may not translate into superior process performance. We propose a multiscale Bayesian Optimization (BO) framework that explicitly couples molecular- and process-level design in a bi-level structure. The inner loop solves deterministic process models, while the outer BO loop explores molecular descriptors, reducing dimensionality, improving sample efficiency, and handling process constraints. A case study on multiscale reactor and catalyst codesign demonstrates that this hybrid strategy achieves optimal performance with substantially lower computational effort than direct BO over the full decision space. BO, when aligned with the natural process—material hierarchy—thus provides an efficient methodology for multiscale design.
Keywords:
Bayesian optimization
bi-level optimization
material design
multiscale modeling
process design