Machine Learning Accelerated Descriptor Design for Catalyst Discovery in CO${}_2$ to Methanol Conversion

Abstract

Transforming CO${}_2$ into methanol represents a crucial step towards closing the carbon cycle, with thermoreduction technology nearing industrial application. However, obtaining high methanol yields and ensuring the stability of heterocatalysts remain significant challenges. Herein, we present a sophisticated computational framework to accelerate the discovery of thermal heterogeneous catalysts, using machine-learned force fields. We propose a new catalytic descriptor, termed adsorption energy distribution, that aggregates the binding energies for different catalyst facets, binding sites, and adsorbates. The descriptor is versatile and can be adjusted to a specific reaction through careful choice of the key-step reactants and reaction intermediates. By applying unsupervised machine learning and statistical analysis to a dataset comprising nearly 160 metallic alloys, we offer a powerful tool for catalyst discovery. We propose new promising candidates such as ZnRh and ZnPt${}_3$, which to our knowledge, have not yet been tested, and discuss their possible advantage in terms of stability.

24 pages, 4 figures + 6 pages, 1 figure (supplementary). Revised version: Updated the journal reference

References in corpus (5)

• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts
• Beyond scaling relations for the description of catalytic materials
• AdsorbML: A Leap in Efficiency for Adsorption Energy Calculations using Generalizable Machine Learning Potentials
• Predicting electronic structures at any length scale with machine learning