Automated Machine Learning of Interfacial Interaction Descriptors and Energies in Metal-Catalyzed N and CO Reduction Reactions.

The applications of machine learning (ML) in complex interfacial interactions are hindered by the time-consuming process of manual feature selection and model construction. An automated ML program was implemented with four subsequent steps: data distribution analysis, dimensionality reduction and clustering, feature selection, and model optimization. Without the need of manual intervention, the descriptors of metal charge variance (Δ) and electronegativity of substrate (χ) and metal (δχ) were raised up with good performance in predicting electrochemical reaction energies for both nitrogen reduction reaction (NRR) and CO reduction reaction (CORR) on metal-zeolites and MoS surfaces. The important role of interfacial interactions in tuning the catalytic reactivity in NRR and CORR was highlighted from SHAP analysis. It was proposed that Fe-, Cr-, Zn-, Nb-, and Ta-zeolites are favorable catalysts for NRR, while Ni-zeolite showed a preference for CORR. An elongated bond of N or a bent configuration of CO was shown in V-, Co-, and Mo-zeolites, indicating that the molecule could be activated after the adsorption in both NRR and CORR pathways. The generalizability of the automatically built ML model is demonstrated from applications to other catalytic systems such as metal-organic frameworks and SiO surfaces. The automated ML program is a useful tool to accelerate the data-driven exploration of relationship between structures and material properties without the need of manual feature selection.