Interpretable machine learned predictions of adsorption energies at the metal--oxide interface

Abstract

The conversion of $\mathrm{C}{\mathrm{O}}_2$ to value-added compounds is an important part of the effort to store and reuse atmospheric $\mathrm{C}{\mathrm{O}}_2$ emissions. Here we focus on $\mathrm{C}{\mathrm{O}}_2$ hydrogenation over so-called inverse catalysts: transition metal oxide clusters supported on metal surfaces. The conventional approach for computational screening of such candidate catalyst materials involves a reliance on density functional theory (DFT) to obtain accurate adsorption energies at a significant computational cost. Here we present a machine learning (ML)-accelerated workflow for obtaining adsorption energies at the metal--oxide interface. We enumerate possible binding sites at the clusters and use DFT to sample a subset of these with diverse local adsorbate environments. The data set is used to explore interpretable and black-box ML models with the aim to reveal the electronic and structural factors controlling adsorption at metal--oxide interfaces. Furthermore, the explored ML models can be used for low-cost prediction of adsorption energies on structures outside of the original training data set. The workflow presented here, along with the insights into trends in adsorption energies at metal--oxide interfaces, will be useful for identifying active sites, predicting parameters required for microkinetic modeling of reactions on complex catalyst materials, and accelerating data-driven catalyst design.

arXiv comment12 pages, 6 figures, 3 tables + supplementary material (15 pages, 13 figures, 6 tables) -- submitted to JCP

References in corpus (11)

• Scikit-learn: Machine Learning in Python
• XGBoost: A Scalable Tree Boosting System
• On representing chemical environments
• A real-space grid implementation of the Projector Augmented Wave method
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
• GPAW: An open Python package for electronic-structure calculations
• Beyond scaling relations for the description of catalytic materials
• Optimizing many-body atomic descriptors for enhanced computational performance of machine learning based interatomic potentials
• Wasserstein Weisfeiler-Lehman Graph Kernels
• Predicting binding motifs of complex adsorbates using machine learning with a physics-inspired graph representation

Cited by in corpus (1)

• Breaking scaling relations with inverse catalysts: a machine learning exploration of trends in $\mathrm{C}{\mathrm{O}}_2$ hydrogenation energy barriers