Chem
ArticleTheory-Guided Machine Learning Finds Geometric Structure-Property Relationships for Chemisorption on Subsurface Alloys
The Bigger Picture
The quantification of adsorbate-surface interactions has been an active field of research for over a century, with a degree of importance that cannot be understated. For example, adsorption theories are instrumental in enabling rational catalyst design, understanding corrosion, and, in general, helping us understand what features of a surface affect the adsorption properties. Nevertheless, developing theories that can link the structure and composition of different materials to their adsorption properties remains a critical and unresolved challenge. In this work, we employ an interpretable class of machine learning models called generalized additive models (iGAM) to explain and quantify alloy-induced changes to the adsorption properties of subsurface metal alloys. These iGAM models yield a comprehensive view of how structural and compositional changes to the local chemical environment of an alloy impact its adsorption properties.
Graphical Abstract
Keywords
UN Sustainable Development Goals
Cited by (0)
- 3
Lead Contact