From biomass waste to CO2 capture: a multi-fidelity machine learning workflow for high-throughput screening of activated carbons
npj Computational Materials, Vol. 11, pp. 363,
Faezeh Hajiali, Naoko Ellis, R. Bhushan Gopaluni
Abstract
This study presents a machine learning-driven framework combining a multi-headed one-dimensional convolutional neural network with multi-fidelity Bayesian optimization for high-throughput screening of biomass-derived activated carbons for CO2 capture applications.