Adaptive Catalyst Discovery Using Multicriteria Bayesian Optimization with Representation Learning
This work addresses the problem of inefficient catalyst discovery for sustainable energy conversion and human health, representing an incremental improvement through hybrid methods.
The study tackled the challenge of discovering high-performance catalysts by proposing an approach that integrates density functional theory and Bayesian optimization with an uncertainty-aware machine learning model, resulting in a 10x reduction in required DFT calculations for catalyst discovery in CO2 reduction.
High-performance catalysts are crucial for sustainable energy conversion and human health. However, the discovery of catalysts faces challenges due to the absence of efficient approaches to navigating vast and high-dimensional structure and composition spaces. In this study, we propose a high-throughput computational catalyst screening approach integrating density functional theory (DFT) and Bayesian Optimization (BO). Within the BO framework, we propose an uncertainty-aware atomistic machine learning model, UPNet, which enables automated representation learning directly from high-dimensional catalyst structures and achieves principled uncertainty quantification. Utilizing a constrained expected improvement acquisition function, our BO framework simultaneously considers multiple evaluation criteria. Using the proposed methods, we explore catalyst discovery for the CO2 reduction reaction. The results demonstrate that our approach achieves high prediction accuracy, facilitates interpretable feature extraction, and enables multicriteria design optimization, leading to significant reduction of computing power and time (10x reduction of required DFT calculations) in high-performance catalyst discovery.