Design of Catalysts for Electrochemical Nitric Oxide Reduction to Ammonia Based on Stacked Ensemble Learning
The electrocatalytic reduction of nitric oxide to ammonia (NORR) is a key green energy conversion technology. Its efficiency relies on high-performance electrocatalysts to enhance both ammonia yield (YNH3) and Faradaic efficiency (FNH3). Conventional experimental screening methods are resource- and time-intensive. Here, machine learning combined with SHAP feature analysis was employed to establish a stacked ensemble model integrating multiple algorithms, enabling systematic investigation of key descriptors governing NORR performance based on an experimental dataset. Evaluation of eight model algorithms revealed that the Stacked-SVR model achieved an R² of 0.9223 and RMSE of 0.0608 for predicting YNH3 on the test set, while the Stacked-RF model achieved an R² of 0.9042 and RMSE of 0.0900 for predicting FNH3. The stacked ensemble model integrates strengths of individual algorithms, demonstrating strong prediction performance while avoiding overfitting. SHAP analysis revealed that Cu content in catalyst composition has the most significant impact on catalytic performance. Moreover, the combination of wet chemical reduction synthesis, carbon fiber (CF) conductive substrate, and HCl electrolyte is more favorable for enhancing catalytic activity. Additionally, moderately lowering working potential, controlling electrolyte volume at low-to-medium levels, reducing catalyst loading, and increasing electrolyte concentration synergistically enhance both YNH3 and FNH3.