Prediction of CO₂ Reduction Reaction Intermediates and Products on Transition Metal-Doped γ-GeSe Monolayers: A Combined DFT and Machine Learning Approach

Accurate prediction of free energy changes (Δ<i>G</i>) for the vast network of reaction intermediates in the electrocatalytic CO₂ reduction reaction (CO₂RR) is essential for evaluating catalytic performance. We combined density functional theory (DFT) and machine learning (ML) to screen 25 single-atom catalysts (SACs) on defective γ-GeSe monolayers for CO₂ reduction to methanol, methane, and formic acid. Among nine ML models evaluated with 14 features, the XGBoost performed best (R² = 0.92 and MAE = 0.24 eV), identifying Ni, Ru, and Rh@GeSe as prospective catalysts. Feature importance analysis highlighted CO₂ activation with ∠O-C-O and IP^C-O1 as the key attributes. The trained ML model's Δ<i>G</i> predictions closely match DFT-calculated values for the reported Ti@N₄-C, Fe@g-C₆N₆, and Co@g-C₆N₆. Incorporating non-DFT-based features enabled rapid predictions while retaining model performance. This work identifies effective SACs for CO₂RR and offers insights for efficient catalyst design.