Abstract
The transition toward carbon‐neutral chemical manufacturing calls for innovative strategies to produce nitrogen‐based compounds with minimal environmental impact. Urea, a key nitrogen‐rich chemical, is currently synthesized via the energy‐intensive Bosch‐Meiser process, which relies heavily on fossil fuel‐derived ammonia. As a sustainable alternative, electrochemical urea synthesis (ECUS) enables the direct coupling of nitrogenous and carbonaceous precursors under ambient conditions, yet remains hampered by sluggish kinetics and poor selectivity—particularly in the critical C─N bond formation step. Here, density functional theory (DFT) calculations is integrated with data‐driven machine learning to systematically explore the activity landscape of nitrogen‐doped graphene‐supported dual‐metal‐atom catalysts (M′M@NC) for C─N coupling. A comprehensive reaction network is evaluated across 45 M′M@NC configurations, revealing three heteronuclear catalysts—VNi@NC, CoNi@NC and CoCu@NC—with consistently favorable thermodynamic and kinetic performance. Electronic structure analysis indicates that heteronuclear coordination promotes *CO activation and optimizes *NH x adsorption, facilitating C─N coupling. Leveraging symbolic regression via the sure independence screening and sparsifying operator (SISSO) algorithm, interpretable descriptors linking C─N coupling energy to atomic‐level electronic properties is established, highlighting the critical role of d‐electron asymmetry. This results uncover fundamental design principles for dual‐atom catalysts and provide a predictive framework for guiding the development of next‐generation electrocatalysts for sustainable urea synthesis.

This publication has 57 references indexed in Scilit: