Featurization and Regression Analysis of Stability of Dilute Bimetallic Catalyst Surfaces

APS  ·  2022

Isabel Diersen; Cameron Owen; Steven Torrisi; Jin Soo Lim; Lixin Sun; Boris Kozinsky;

HIGHLIGHT

We attempt to determine which alloy parameters determine configuration stability, using machine learning (ML) models that take as input elemental and structural properties that are quick to compute and easily accessible compared to those calculated using first-principles methods.

RELATED

Papers      Patents     Grants     Venues     Experts    Cite    Share    Save

ABSTRACT

Among catalytic materials, dilute transition metal alloys can evince improved catalytic performance compared to their monometallic counterparts. Crucial questions remain surrounding the stability of individual active surface configurations. We attempt to determine which alloy parameters determine configuration stability, using machine learning (ML) models that take as input elemental and structural properties that are quick to compute and easily accessible compared to those calculated using first-principles methods. Using structure files from a dataset consisting of thousands of unique configurations of dilute bimetallic surface alloys, our featurization workflow creates over 180 predictors for regression analysis of the structures’ formation energies and a classification task to predict the lowest energy configuration. Our results from several ML regression and classification techniques contribute to both predictive modeling and feature selection, allowing for the discovery of new design rules.

 Paraphrase     Questionfy     Wikify     Simplify     Summarize