Rapid prediction of molecule arrangements on metal surfaces via Bayesian optimization. (30th May 2017)

• Record Type: Journal Article
• Authors: Packwood, Daniel M.; Hitosugi, Taro
• Is Part Of: Applied physics express. Volume 10:Number 6(2017)
• Publication Date: 2017-05-30
• Subjects: Physics -- Periodicals; Technology -- Periodicals; 621.05
• DOI: 10.7567/APEX.10.065502
• Languages: English
• ISSNs: 1882-0778

Abstract

Abstract: The spatial arrangement of molecule adsorbates on a metal surface is very difficult to predict via first-principles calculations and standard optimizing algorithms. In this Letter, we show that a machine learning technique called Bayesian optimization can optimize the arrangement of two medium-sized aromatic adsorbates on a copper (111) surface within tens of density functional theory energy evaluations. The methodology reported here is therefore a step toward first-principles structure predictions for chemically modified surfaces, without the need to first specify the arrangement of molecule adsorbates from experimental data.