Resolving the Coverage Dependence of Surface Reaction Kinetics with Machine Learning and Automated Quantum Chemistry Workflows

Microkinetic models for catalytic systems require estimation of many thermodynamic and kinetic parameters that can be calculated for isolated species and transition states using ab initio methods. However, the presence of nearby co-adsorbates on the surface can dramatically alter these thermodynamic and kinetic parameters causing them to be dependent on species coverage fractions. As there are combinatorially many co-adsorbed configurations on the surface, computing the coverage dependence of these parameters is far less straightforward. We present a framework for generating and applying machine learning models to predict coverage dependent parameters for microkinetic models. Our toolkit enables automatic calculation and evaluation of co-adsorbed configurations allowing us to sample 2000 co-adsorbed adsorbates and transition states (TSs) for a diverse set of 9 reactions on Cu111, a challenging surface, with four possible co-adsorbates. This dataset was then used to train subgraph isomorphic decision trees (SIDTs) to predict the stability and association energy of configurations. With which we were able to achieve mean absolute errors (MAEs) of 0.106 eV on adsorbates, 0.172 eV on TSs, and due to natural error cancellation in SIDTs for relative properties 0.130 eV on reaction energies and 0.180 eV on activation barriers. We then explain how to use these models to predict coverage dependent corrections for arbitrary adsorbates and TSs and demonstrate on H∗, HO∗ and O∗ comparing the generated SIDT model with an iteratively refined version.