Directly predicting N₂ electroreduction reaction free energy using interpretable machine learning with non-DFT calculated features

Electrocatalytic nitrogen reduction to ammonia has garnered significant attention with the blooming of single-atom catalysts (SACs), showcasing their potential for sustainable and energy-efficient ammonia production. However, cost-effectively designing and screening efficient electrocatalysts remains a challenge. In this study, we have successfully established interpretable machine learning (ML) models to evaluate the catalytic activity of SACs by directly and accurately predicting reaction Gibbs free energy. Our models were trained using non-density functional theory (DFT) calculated features from a dataset comprising 90 graphene-supported SACs. Our results underscore the superior prediction accuracy of the gradient boosting regression (GBR) model for both ΔG(N₂→NNH) and ΔG(NH₂→NH₃), boasting coefficient of determination (R²) score of 0.972 and 0.984, along with root mean square error (RMSE) of 0.051 and 0.085 eV, respectively. Moreover, feature importance analysis elucidates that the high accuracy of GBR model stems from its adept capture of characteristics pertinent to the active center and coordination environment, unveilling the significance of elementary descriptors, with the colvalent radius playing a dominant role. Additionally, Shapley additive explanations (SHAP) analysis provides global and local interpretation of the working mechanism of the GBR model. Our analysis identifies that a pyrrole-type coordination (flag = 0), d-orbitals with a moderate occupation (N_d = 5), and a moderate difference in covalent radius (r_TM-ave near 140 pm) are conducive to achieving high activity. Furthermore, we extend the prediction of activity to more catalysts without additional DFT calculations, validating the reliability of our feature engineering, model training, and design strategy. These findings not only highlight new opportunity for accelerating catalyst design using non-DFT calculated features, but also shed light on the working mechanism of “black box” ML model. Moreover, the model provides valuable guidance for catalytic material design in multiple proton-electron coupling reactions, particularly in driving sustainable CO₂, O₂, and N₂ conversion.

© 2024 Science Press  and Dalian Institute of Chemical Physics, Chinese Academy of Sciences. Published by ELSEVIER B.V. and Science Press. All rights are reserved, including those for text and data mining, AI training, and similar technologies.