The aim is to optimize microalgae cultivation for stable biomass yields amidst industrial variability.
Utilized a dual-uncertainty quantified random forest framework.
Applied robust optimization techniques.
Addressed noise factors present in industrial settings.
Achieved stable and reproducible biomass yields.
Validated the optimization framework under various uncertainties.
Resumen
A dual-uncertainty quantified random forest-based EGO framework robustly optimizes microalgae cultivation, ensuring stable and reproducible biomass yields in the presence of industrial noise.