Predicting binding motifs of complex adsorbates using machine learning with a physics-inspired graph representation

Abstract

Computational screening in heterogeneous catalysis relies increasingly on machine learning models for predicting key input parameters due to the high cost of computing these directly using first-principles methods. This becomes especially relevant when considering complex materials spaces, e.g. alloys, or complex reaction mechanisms with adsorbates that may exhibit bi- or higher-dentate adsorption motifs. Here we present a data-efficient approach to the prediction of binding motifs and associated adsorption enthalpies of complex adsorbates at transition metals (TMs) and their alloys based on a customized Wasserstein Weisfeiler-Lehman graph kernel and Gaussian Process Regression. The model shows good predictive performance, not only for the elemental TMs on which it was trained, but also for an alloy based on these TMs. Furthermore, incorporation of minimal new training data allows for predicting an out-of-domain TM. We believe the model may be useful in active learning approaches, for which we present an ensemble uncertainty estimation approach.

update open source repository and reference

References in corpus (5)

• Quantum ESPRESSO: a modular and open-source software project for quantum simulations of materials
• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• Beyond scaling relations for the description of catalytic materials
• Infusing Theory into Deep Learning for Interpretable Reactivity Prediction
• GemNet: Universal Directional Graph Neural Networks for Molecules

Cited by in corpus (5)

• AdsorbML: A Leap in Efficiency for Adsorption Energy Calculations using Generalizable Machine Learning Potentials
• Accelerating structure search using atomistic graph-based classifiers
• Transition States Energies from Machine Learning: An Application to Reverse Water-Gas Shift on Single-Atom Alloys
• A Fuzzy Classification Framework to Identify Equivalent Atoms in Complex Materials and Molecules
• Interpretable machine learned predictions of adsorption energies at the metal--oxide interface