Machine learning-guided two-dimensional single-atom catalysts for electrochemical CO2 utilisation.
Abstract
The electrochemical CO2 reduction reaction (CO2RR) offers a promising route to convert greenhouse gas emissions into value-added fuels and chemicals, yet achieving high product selectivity while suppressing the competing hydrogen evolution reaction (HER) remains a central challenge. Two-dimensional (2D) material-supported single-atom catalysts (SACs) address this challenge through atomically defined coordination environments that enable precise tuning of the critical *COOH and *CO adsorption energies, which strongly influence CO2 activation and product selectivity, while the competing adsorption of *H governs HER suppression. This review examines the convergence of 2D-SAC design and machine learning (ML) for CO2RR catalyst discovery. We first outline the mechanistic foundations of the CO2RR together with comparative insights from the HER and OER and then discuss the structural and electronic principles governing single-atom stabilisation on nitrogen-rich carbon, transition metal dichalcogenide, and MXene supports. Recent catalytic advances are assessed with the CO2RR as the primary focus, including proximity-engineered systems that promote C-C coupling and multicarbon product formation. Finally, emerging ML frameworks are critically reviewed, covering electronic, geometric, and spectroscopic descriptor design, data source strategies, and high-throughput screening and inverse-design workflows. Operando ML integration has revealed the dynamic evolution of active sites under reaction conditions, highlighting the need to incorporate electrochemical-environment and reaction-condition-dependent structural information into future training datasets. Key priorities identified for the field are large-scale CO2RR-specific SAC database construction, product- and condition-specific descriptor development, and closure of the prediction-synthesis-validation feedback loop.