.png){kind=icon}
Return
Multi-objective reaction optimization under uncertainties using expected quantile improvement
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compchemeng.2024.108983.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multi-objective Bayesian optimization (MOBO) has shown to be a promising tool for reaction development. However, noise is usually inevitable in experimental and chemical processes, and finding reliable solutions is challenging when the noise is unknown or significant. In this study, we focus on finding a set of optimal reaction conditions using multi-objective Euclidian expected quantile improvement (MO-E-EQI) under noisy settings. First, the performance of MO-E-EQI is evaluated by comparing with some recent MOBO algorithms in silico with linear and log-linear heteroscedastic noise structures and different magnitudes. It is noticed that high noise can degrade the performance of MOBO algorithms. MO-E-EQI shows robust performance in terms of hypervolume-based metric, coverage metric and number of solutions on the Pareto front. Finally, MO-E-EQI is implemented in areal case to optimize an esterification reaction to achieve the maximum space-time-yield and the minimal E-factor. The algorithm identifies a clear trade-off between the two objectives.
Keywords:
Multi-objective Bayesian optimization
Reaction development
Heteroscedastic noise
Machine learning
Journal
C
IF:
3.9
Papers:
8.1K
Citations:
1.7W
Organization
Cited Papers
Monoclonal IgM with unique specificity to gangliosides GM
1
and GD
1b
and to lacto‐
N
‐tetraose associated with human motor neuron disease.png)
Neurology
NeurologyIF0
PREAI
ShareSaveShareSave
ShareSaveShareSaveShareSave
View more