Accurate Prediction of Adsorption and Diffusion Energies of Single Metal Atoms Supported on MXenes from Machine Learning

Single atom catalysts (SACs) are frontier composites maximizing the active phase activity, but require stabilization. This study conducted a high-throughput analysis of 54 pristine MXenes as supports for the 30 3 d , 4 d , and 5 d transition metals (TMs), exploring 1620 cases. First-principles calculations on MXene models showed patterns in the adsorption energies, E ads , of the TM single-atom (SA), revealing high E ads , except for d 5 or d 10 TM electronic configurations. The SA diffusion barriers, E b , revealed easy diffusions, although in some cases high E b inhibited aggregation or dispersion. Random forest regressor (RFR) machine learning predicted E ads with a mean absolute error (MAE) of 0.25 eV, and a regression coefficient of 0.99, showing that the TM cohesive energy is key in E ads prediction. Here, the RFR model reported a MAE of 0.1 eV, with few MXene and SA properties being important. Our findings provide insights to use MXenes as support for SACs or TM clusters.