Machine Learning Accelerated Screening Advanced Single-Atom Anchored MXenes Electrocatalyst for Nitrogen Fixation

Electrochemical nitrogen reduction reaction (NRR) has garnered significant attention as an alternative to the energy-intensive Haber–Bosch process. However, the vast search space for electrocatalysts and unclear structure–activity relationships limit the rational design of electrocatalysts for NRR. Herein, we present a machine learning-driven catalyst screening process to achieve high-throughput screening of two-dimensional material (MXene) supported single-atom catalysts (MXene-SACs) targeting NRR performance. Utilizing a database from density functional theory calculations as input, we identified four top-performing catalysts from 3146 MXene-SACs and recognized an effective intrinsic descriptor to accelerate high-throughput screening without additional computations, which was further validated experimentally by 10 synthesized MXene-SACs. In-depth study of the descriptor revealed a NRR mechanism: electron transfer from the single atom to coordinating atoms, causing crystal field splitting into e g and t 2 g bands. The interaction between the empty e g band of the single atom and the N 2 H π* orbital, activated by electrons from the t 2 g occupied orbital, facilitates the N≡N bond, promoting a smooth reaction under weak N 2 adsorption. Impressively, the screened Mo 2 CO 2 –Zr, with strong atomic interactions, achieved a superior Faradaic efficiency of 31.7%. This work can not only provide a deeper understanding of the catalytic processes but also offer a foundation for future catalyst design and synthesis.