Constant-Potential Machine Learning Force Field for the Electrochemical Interface

Better understanding and prediction of the electrochemical interface require large-scale atomistic simulations. Machine learning force fields (MLFFs) have proven to be an effective approach. However, current MLFFs typically do not account for the effect of electrode potential, which requires treating interface electrons with a grand canonical ensemble. Here, we develop a constant potential MLFF (CP-MLFF) based on an equivariant graph neural network and implement it into MACE. Specifically, we design an architecture that can take the number of electrons as the input and accurately predict the Fermi level. The CP-MLFF allows us to examine the convergency of the electrochemical barrier with respect to sampling, which we demonstrate through the example of CO2 reduction on the Ni–N–C catalyst. Our work provides a useful method and tool enabling accurate and efficient large-scale simulation of the electrochemical interface.