Identifying the Catalytic Descriptor of Single-Atom Catalysts in Nitrate Reduction Reaction: An Interpretable Machine-Learning Method

TL;DR

This study uses an interpretable machine learning approach to identify key factors influencing nitrate reduction catalysis on single-atom catalysts, leading to the discovery of promising cost-effective catalysts with superior predicted activity.

Contribution

It introduces a novel interpretable machine learning method to determine catalytic descriptors for nitrate reduction, enabling the prediction of high-performance, low-cost catalysts.

Findings

Identified three critical factors for nitrate reduction activity: low N_V, moderate D_N, and specific doping patterns.

Developed a new descriptor ($c6$) combining intrinsic properties and geometric angles.

Predicted 16 promising catalysts with ultra-low limiting potentials, surpassing existing catalysts.

Abstract

Elucidating the catalytic descriptor that accurately characterizes the structure-activity relationships of typical catalysts for various important heterogeneous catalytic reactions is pivotal for designing high-efficient catalytic systems. Here, an interpretable machine learning technique was employed to identify the key determinants governing the nitrate reduction reaction ($\rm NO_3RR$) performance across 286 single-atom catalysts (SACs) with the active sites anchored on double-vacancy $\rm BC_3$ monolayers. Through Shapley Additive Explanations (SHAP) analysis with reliable predictive accuracy, we quantitatively demonstrated that, favorable $\rm NO_3RR$ activity stems from a delicate balance among three critical factors: low $\rm N_V$, moderate $\rm D_N$, and specific doping patterns. Building upon these insights, we established a descriptor ($\psi$) that integrates the intrinsic catalytic properties and the intermediate O-N-H angle ($\theta$), effectively capturing the underlying structure-activity relationship. Guided by this, we further identified 16 promising catalysts with predicted low limiting potential ($U_{\rm L}$). Importantly, these catalysts are composed of cost-effective non-precious metal elements and are predicted to surpass most reported catalysts, with the best-performing Ti-V-1N1 is predicted to have an ultra-low $U_{\rm L}$ of $-0.10$ V.