Active Learning Accelerating to Screen Dual-Metal-Site Catalysts for Electrochemical Carbon Dioxide Reduction Reaction

Integrating Active Learning and DFT for Fast-Tracking Single-Atom Alloy Catalysts in CO2-to-Fuel Conversion

Electrocatalytic carbon dioxide reduction (CO2RR) technology enables the conversion of excessive CO2 into high-value fuels and chemicals, thereby mitigating atmospheric CO2 concentrations and addressing energy scarcity. Single-atom alloys (SAAs) possess the potential to enhance the CO2RR performance by full utilization of atoms and breaking linear scaling relationships. However, quickly screening high-performance metal portfolios of SAAs remains a formidable challenge. In this study, we proposed an active learning (AL) framework to screen high-performance catalysts for CO2RR to yield fuels such as CH4 and CH3OH. After four rounds of AL iterations, the ML model attained optimal prediction performance with the test set R2 of approximately 0.94 and successful prediction was achieved for the binding free energy of *CHO, *COH, *CO, and *H on 380 catalyst surfaces with an accuracy within 0.20 eV. Subsequent analysis of the SAA catalysts' activity, selectivity, and stability led to the discovery of eight previously unexplored SAA catalysts for CO2RR. Notably, the surface activity of Ti@Cu(100), Au@Pt(100), and Ag@Pt(100) shines prominently. Utilizing DFT calculations, we elucidated the complete reaction pathway of the CO2RR on the surfaces of these catalysts, confirming their high catalytic activity with limiting potentials of -0.11, -0.34, and -0.46 eV, respectively, which are significantly lower than those of pure Cu catalysts. The results showcase the exceptional predictive prowess of AL, providing a valuable reference for the design of CO2RR catalysts.

Influence factors of CO adsorption on C2N-supported dual-atom catalysts unveiled by machine learning and twofold feature engineering

Dual-atom catalysts (DACs) have emerged as a compelling frontier in the realm of the electrochemical carbon dioxide reduction reaction (CO2RR). However, elucidating the intrinsic properties of dual-atom pairs and their direct correlation with catalytic activity poses significant challenges. Herein, we investigate CO adsorption on 248 kinds of C2N-supported DACs and analyze the underlying structure-activity relationships of dual transition metal (TM) atoms based on density functional theory (DFT) calculations and machine learning (ML) models. Compared to the direct input of atomic features in the decision tree model of ML, we confirm that extra feature engineering with the introduction of the arithmetic combination of atomic features can better reflect the correlation of dual TM atoms on C2N-based DACs. Further feature importance analysis reveals a strong relationship between the last one occupied orbital radius (rv), group number (G) for dual TM atoms and the CO binding strength, as well as a potential connection with the d band centre (εd). Our work provides deeper insights into the design of DACs and highlights the significance of twofold feature engineering for the synergistic effects between dual TM atoms.

Efficient exploration of transition-metal decorated MXene for carbon monoxide sensing using integrated active learning and density functional theory

The urgent demand for chemical safety necessitates the real-time detection of carbon monoxide (CO), a highly toxic gas. MXene, a 2D material, has shown potential for gas sensing applications (e.g., NH3, NO, SO2, CO2) due to its high surface accessibility, electrical conductivity, stability, and flexibility in surface functionalization. However, the pristine MXene generally exhibits poor interaction with CO; still, transition metal decoration can strengthen the interaction between CO and MXene. This study presents a high-throughput screening of 450 combinations of transition-metal (TM) decorated MXene (TM@MXene) for CO sensing applications using an integrated active learning (AL) and density functional theory (DFT) screening pipeline. Our AL pipeline, adopting a crystal graph convolutional neural network (CGCNN) as a surrogate model, successfully accelerates the screening of CO sensor candidates with minimal computational resources. This study identifies Sc@Zr3C2O2 and Y@Zr3C2O2 as the optimal TM@MXene candidates with promising CO sensing performance regarding the screening criteria of recovery time, surface stability, charge transfer, and sensitivity to CO. The proposed AL framework can be extended for property finetuning in the combinatorial chemical space.