Identifying the Catalytic Descriptor of Single-Atom Catalysts in Nitrate Reduction Reaction: An Interpretable Machine-Learning Method
Zhen Zhu, Shan Gao, Jing Zhang, Xuxin Kang, Shunfang Li, Xiangmei Duan
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 (NO 3 RR) performance across 286 single-atom catalysts (SACs) with the active sites anchored on double-vacancy BC 3 monolayers. Through Shapley Additive Explanations (SHAP) analysis with reliable predictive accuracy, we quantitatively demonstrated that, favorable NO 3 RR activity stemmed from a delicate balance among three critical factors: low N V, moderate D N, and specific doping patterns. Building upon these insights, we established a descriptor (ψ) that integrated the intrinsic catalytic properties and the intermediate O–N–H angle (θ), effectively capturing the underlying structure–activity relationship. Guided by this, we further identified 16 promising catalysts with predicted low limiting potential ( U L ). Importantly, these catalysts are composed of cost-effective nonprecious metal elements and are predicted to surpass most reported catalysts, with the best-performing Ti–V-1N1 is predicted to have an ultralow U L of −0.10 V.