Data-driven design of double-atom catalysts with high H<sub>2</sub> evolution activity/CO<sub>2</sub> reduction selectivity based on simple features
Chenyang Wei, Dingyi Shi, Zhaohui Yang, Zhimin Xue, Shuzi Liu, Ruiqi Li, Tiancheng Mu
Abstract
Double-atom catalysts (DACs) were designed and analyzed using DFT and machine learning (ML) methods. ML can not only identify the activity center for DACs but also help screen DACs with higher HER or CO 2 RR activity.
Topics & Concepts
Atom (system on chip)SelectivityCatalysisReduction (mathematics)ChemistryCenter (category theory)Computer scienceCombinatorial chemistryMaterials scienceCrystallographyMathematicsEmbedded systemOrganic chemistryGeometryCO2 Reduction Techniques and CatalystsElectrocatalysts for Energy ConversionMachine Learning in Materials Science